Road disaster response support system and program, road management support method

Abstract

Previously, road service providers conducted rescue operations by assessing the situation on-site after a rescue request was made and making personal decisions, which resulted in issues such as delayed initial response, getting stranded in impassable areas, and difficulty prioritizing rescue requests. Furthermore, there was no system in place to utilize video footage, location information, or member report information available on-site before carrying out rescue operations. [Solution] The present invention comprises an information acquisition unit that integrates and acquires at least two or more of rescue request reception information, rescue operation acquisition information acquired by rescue vehicles, etc., and member notification information, and an analysis unit that analyzes these using AI to evaluate the possibility of a road disaster occurring, the extent of its impact, and the priority of rescue operations. Based on the analysis results, the system determines whether rescue vehicles can pass and the optimal route, and outputs information to support rescue operations, prioritization, and the deployment of equipment, materials, and personnel, thereby providing a road disaster response support system that supports rapid and rational rescue operations.

Description

[Technical Field]

[0001] The present invention relates to technology for supporting rescue operations when a disaster occurs on a road, and in particular to a road disaster response support system, related programs, and road management support methods that integrate and analyze multiple pieces of information, such as rescue request reception information managed by road service providers, various information obtained at rescue operation sites, and information reported by members, to support optimal deployment of rescue vehicles, route selection, judgment on whether rescue operations can be carried out, and evaluation of the disaster impact. The purpose of this invention is to expand road service operations, which have traditionally been limited to rescue operations at disaster sites, to include the collection, analysis, and utilization of disaster information, thereby enabling the sophistication of rescue operations and overall road disaster response, and the speed of initial responses. [Background technology]

[0002] Until now, road service providers have primarily focused on providing emergency response at the scene of vehicle breakdowns or accidents, but even in disasters, there are many cases where on-site rescue is difficult due to road blockages, traffic disruptions, etc. Previously, it was common for rescue vehicles to only grasp the disaster situation and begin responding after arriving at the scene, and there was no established system for scientifically assessing the situation at the time of a rescue request, selecting an appropriate route, or supporting collaboration with other organizations. In addition, on-site information obtained from dashcam footage installed in rescue vehicles and small unmanned aerial vehicles (drones), as well as report information provided by members, were only used to a limited extent after rescue operations, and there was no system in place to comprehensively utilize and analyze this information before or during rescue operations and evaluate the disaster situation and road conditions in real time. Furthermore, in recent large-scale natural disasters, requests for rescue have tended to be concentrated in a short period of time, increasing the need to make quick and rational decisions regarding which requests should be prioritized, whether rescue vehicles are passable, which route is optimal, etc. With conventional technology, these decisions largely depended on the experience and intuition of rescue team members, making it difficult to optimize them according to the situation. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Japan Automobile Federation, "Disaster Relief and Training by Special Support Teams," JAF also operates in areas affected by earthquakes, typhoons, etc., [online], publication date unknown, Japan, [Retrieved June 15, 2025], Internet<URL:https: / / jaf.or.jp / common / about-road-service / training> Summary of the Invention [Problem to be solved by the invention]

[0004] When a large-scale disaster occurs, road blockages, flooding, collapsed bridges, etc. make it difficult for rescue vehicles to pass, and there is a risk that rescue operations will be disrupted by a concentration of rescue requests. Furthermore, while on-site information that can be obtained during rescue operations (such as dashcam footage and drone footage) and reports from members themselves who are requesting rescue are important information for streamlining and optimizing rescue operations, until now there has been no system in place to analyze this information before rescue operations begin and use it to provide support. Furthermore, processes such as determining the priority of rescue operations, determining whether rescue vehicles can pass through, and selecting the optimal route still depend on personal judgment, making it difficult to achieve efficient and rational disaster response.Furthermore, there was a lack of information-sharing infrastructure to quickly and accurately provide members and government agencies with information on the status of rescue operations and whether roads were passable. The present invention aims to solve these problems and provide a road disaster response support system, related programs, and road management support methods that support rescue operations by comprehensively analyzing rescue request reception information, rescue operation acquisition information, and member report information, enabling appropriate operation of rescue vehicles and rapid disaster response. [Means for solving the problem]

[0005] In order to solve the above problems, a road disaster response support system according to the present invention has the following configuration. an information acquisition unit that integrates and acquires at least two or more of rescue request reception information sent by rescue requesters (e.g., members), rescue activity acquisition information acquired on-site using rescue vehicles or drive recorders, small unmanned aerial vehicle camera devices, portable information devices, etc., and member notification information; The system is configured to include an analysis unit that evaluates the possibility of the road disaster occurring, the scale of damage, the degree of impact on traffic, the priority of rescue operations, etc., based on the information acquired by the information acquisition unit. The analysis unit is also configured to calculate the density of rescue requests using geographical information, disaster details, time of occurrence, etc. contained in the rescue request reception information, rescue operation acquisition information, or member notification information, and to derive a road disaster score based on this. Furthermore, based on the road disaster score, the equipment and personnel available at the branch or base, information can be output to support optimal deployment planning for rescue vehicles and personnel. The system also uses an AI (artificial intelligence) model to analyze information obtained at the site of rescue operations, determine whether rescue vehicles can pass through, and, based on the results, assists in determining whether rescue operations are possible, prioritizing them, and selecting passable routes. Furthermore, the system can be configured to provide rescue operation scores, success / failure decisions, and support information to the rescue control room or administrator as a visualized dashboard, or to send the information directly to on-site personnel or member terminals. In addition, a configuration can be adopted that includes an improvement unit that retrains or updates the AI ​​model using collected information and the results of rescue operations, thereby improving the accuracy of analysis. This configuration will enable a consistent process from receiving rescue requests to understanding the situation on site, evaluation using AI (artificial intelligence), selecting the optimal route and vehicle, and notifying the results, thereby speeding up and streamlining rescue operations and helping to solve existing issues. [1] A road disaster support system characterized by comprising: an information acquisition unit that acquires at least two or more pieces of information from among rescue request reception information regarding rescue request responses managed by a road service provider, rescue activity acquisition information regarding road disaster conditions or road infrastructure conditions acquired by at least one of the road service provider's rescue vehicle, or a drive recorder installed in the rescue vehicle, or the road service provider's small unmanned aerial vehicle camera, or the road service provider's portable information device, and member report information regarding the road disaster conditions or road infrastructure conditions provided by members of the road service provider; and an analysis unit that analyzes the possibility of a road disaster occurring or the possibility of an abnormality in road infrastructure based on the information acquired by the information acquisition unit. [2] A road disaster support system as described in [1], characterized in that the analysis unit evaluates the likelihood of the occurrence of the road disaster or the scope of the impact of the road disaster based on the information acquired by the information acquisition unit, and based on at least one of the content, geographical concentration, and time period of the road disaster contained in any of the rescue request reception information, the rescue activity acquisition information, and the member report information. [3] [1] A road disaster support system as described in [1], characterized in that the analysis unit calculates the density of requests, rescue activities, or reports based on the information acquired by the information acquisition unit, based on the content, geographical information, and number of occurrences of the road disaster contained in any of the rescue request reception information, the rescue activity acquisition information, and the member report information, and derives a score for the road disaster based on the density. [4] [3] A road disaster support system as described in [3], characterized in that the analysis unit outputs support information for optimizing the deployment of personnel or equipment based on the road disaster score derived based on the density, as well as information on the equipment held at each branch or base and information on the personnel available to respond. [5] [1] A road disaster support system as described in [1], wherein the analysis unit uses artificial intelligence to analyze the content related to the road disaster contained in any of the rescue request reception information, the rescue operation acquisition information, and the member report information based on the information acquired by the information acquisition unit, determines whether the rescue vehicle of the road service provider is passable, and based on the result of the determination, outputs whether rescue operations are possible, the priority of the rescue operations, or the selection of the rescue vehicle to be used for the rescue operations. [6] [5] A road disaster support system as described in [5], characterized in that the analysis unit selects a passable route for the rescue vehicle based on rescue location information, support base information, and traffic regulation information, and further based on the results of analyzing the rescue activity acquisition information. [7] [1] A road disaster support system as described in [1], characterized in that the road disaster support system is provided with a dashboard that visualizes the road disaster score, the support information, the judgment results regarding rescue activities, and passable route information output by the analysis unit and the decision unit based on the information acquired by the information acquisition unit. [8] [4] A road disaster support system as described in [4], characterized in that the analysis unit selects a response measure suitable for rescue operations from among multiple response measures based on the road disaster score and the support information, and outputs response proposal information regarding the implementation of the response measure. [9] [1] A road disaster support system as described in [1], characterized in that the improvement unit is configured to perform learning or updating of the artificial intelligence analysis model based on the information acquired by the information acquisition unit and the results of analysis by the analysis unit, and based on any of the rescue request reception information, the rescue activity acquisition information, and the member report information, thereby improving the accuracy of road disaster determination or the accuracy of optimizing rescue activities.

[10] [1] A road disaster support system as described in [1], characterized in that the road disaster support system has a communication function for transmitting the judgment results regarding the rescue activities, the passable route information, or the response proposal information output by the analysis unit or the decision unit based on the information acquired by the information acquisition unit to a portable information device carried by the on-site personnel of the road service provider.

[11] [1] A road disaster support system as described in the above [1], characterized in that the road disaster support system has a function of transmitting the traffic regulation information, the road disaster occurrence status, the estimated arrival time of the rescue vehicle, or the passable route information output by the analysis unit or the decision unit based on the information acquired by the information acquisition unit to a mobile terminal device carried by a member of the road service provider.

[12] [1] A road disaster support system as described in [1], characterized in that the road disaster support system has a function of transmitting information regarding the occurrence status of the road disaster, impassable areas, the status of rescue support, or the estimated arrival time of the rescue vehicle output by the analysis unit or the decision unit based on the information acquired by the information acquisition unit to an external system that can be used by road managers, administrative agencies, or disaster response organizations.

[13] [1] A road disaster support system as described in [1], characterized in that the road disaster support system optimizes the coordinated deployment of personnel or equipment across multiple branches or multiple municipalities, as well as the securing of accommodation or support bases for such personnel, based on the road disaster score, the judgment results regarding the rescue activities, and information regarding the equipment held at each branch or base and information regarding the personnel available, which are derived by the analysis unit or the decision unit based on the information acquired by the information acquisition unit, and is equipped with a control coordination function that provides pass permit information or traffic restriction instructions to the pass permit management system or the entry management system of the disaster area.

[14] [1] A road disaster support system as described in [1], characterized in that the road disaster support system is equipped with a control function that automatically switches the operation mode of the road disaster support system from normal mode to disaster mode when the road disaster score derived by the analysis unit based on the information acquired by the information acquisition unit exceeds a predetermined threshold, and changes the priority or notification format of the information to be output.

[15] [1] A road disaster support system as described in [1], characterized in that the road disaster support system collects information regarding the actual occurrence of the road disaster, the results of rescue operations, the passage history of the rescue vehicles, and the analysis results obtained by the analysis unit, stores the information as learning data for an artificial intelligence model used in the analysis unit, and has the function of controlling a model update process for re-learning or updating the artificial intelligence model.

[16] [1] A road disaster support system as described in [1], characterized in that the road disaster support system is equipped with a security linkage function that prevents unauthorized access, prevents tampering with communication content, or performs authentication processing for information sent and received between the system and the external system, the member's mobile terminal device, or the field team member's mobile information device.

[17] [1] A road disaster support system as described in [1], characterized in that the road disaster support system is configured to ensure the continuity of operation of the entire system by redundating the suspension of some functions due to communication failures, power failures, or equipment failures during a disaster using other network routes, alternative servers, or alternative processing mechanisms.

[18] A program for causing a computer to function as the road disaster support system described in [1], characterized in that the computer is capable of sequentially and additionally executing the functions described in [2] to

[17] as necessary.

[19] A road management support method using a computer, comprising: The computer acquires via a network at least two or more pieces of information from the following: rescue request reception information regarding rescue request responses managed by a road service provider; rescue activity acquisition information regarding road disaster conditions or road infrastructure conditions acquired by at least one of the road service provider's rescue vehicle, or a drive recorder installed in the rescue vehicle, or the road service provider's small unmanned aerial vehicle camera, or the road service provider's portable information device; and member report information regarding the road disaster conditions or road infrastructure conditions provided by members of the road service provider; and analyzes the possibility of a road disaster occurring or the possibility of an abnormality in the road infrastructure based on the acquired information.

[20]

[19] A road management support method as described in

[20]

[19] , characterized in that the computer evaluates the likelihood of a road disaster occurring or the extent of its impact based on the information acquired via a network, and based on at least one of the content, geographical concentration, and time period of occurrence related to the road disaster contained in any of the rescue request reception information, the rescue activity acquisition information, and the member report information.

[21]

[19] A road management support method as described in

[19] , characterized in that the computer calculates the density of requests, rescue activities, or reports based on the information acquired via a network, based on the content, geographical information, and number of occurrences of the road disaster contained in any of the rescue request reception information, the rescue activity acquisition information, and the member report information, and derives a score for the road disaster based on the density.

[22]

[21] A road management support method as described in

[22]

[21] , characterized in that the computer outputs support information for optimizing the deployment of personnel or equipment based on the road disaster score derived based on the density, as well as information on the equipment held at each branch or base and information on the personnel available to respond, via a network.

[23]

[19] A road management support method as described in

[19] , characterized in that the computer uses artificial intelligence to analyze the content regarding the road disaster contained in any of the rescue request reception information, the rescue activity acquisition information, and the member notification information based on the information via a network, determine whether the rescue vehicle of the road service provider is passable, and based on the result of the determination, output whether rescue activity is possible, the priority of the rescue activity, or the selection of the rescue vehicle to be used for the rescue activity.

[24]

[23] A road management support method as described in

[24]

[23] , characterized in that the computer selects a passable route for the rescue vehicle based on rescue location information, support base information, and traffic regulation information via a network, and further based on the results of analyzing the rescue activity acquisition information.

[25]

[19] A road management support method according to the present invention, characterized in that the computer is provided with a dashboard that visualizes the road disaster score, the support information, the judgment results regarding rescue operations, and passable route information, which are output based on the acquired information via a network.

[26]

[22] A road management support method as described in

[26]

[22] , characterized in that the computer selects a response measure suitable for rescue operations from among multiple response measures based on the road disaster score and the support information via a network, and outputs response proposal information regarding the implementation of the response measure.

[27]

[19] A road management support method as described in

[19] , characterized in that the computer performs learning or updating of the artificial intelligence analytical model based on the acquired information and analyzed results via a network, based on either the rescue request reception information, the rescue operation acquisition information, or the member report information, thereby improving the accuracy of road disaster determination or the accuracy of rescue operation optimization.

[28]

[19] A road management support method as described in

[19] , characterized in that the computer transmits via a network the judgment results regarding the rescue operations, the passable route information, or the response proposal information output based on the acquired information to a portable information device carried by a field member of the road service provider.

[29]

[19] A road management support method as described in

[19] , characterized in that the computer transmits the traffic regulation information, the road disaster occurrence status, the estimated arrival time of the rescue vehicle, or the passable route information output based on the acquired information via a network to a mobile terminal device carried by a member of the road service provider.

[30]

[19] A road management support method as described in

[19] , characterized in that the computer transmits information regarding the occurrence of the road disaster, impassable areas, the status of rescue support, or the estimated arrival time of the rescue vehicle, which is output based on the acquired information, via a network to an external system that can be used by road managers, administrative agencies, or disaster response agencies.

[31]

[19] A road management support method as described in

[31]

[19] , wherein the computer optimizes the coordinated deployment of personnel or equipment across multiple branches or multiple municipalities, as well as the securing of accommodation or support bases for such personnel, based on the road disaster score, the judgment results regarding the rescue operations, and information regarding the equipment held at each branch or base and information regarding the personnel available to respond, which are derived based on the acquired information, via a network, and provides pass permit information or traffic restriction instructions to the pass permit management system or the entry management system for the disaster area.

[32]

[19] A road management support method as described in

[19] , characterized in that when the road disaster score derived based on the information acquired via the network exceeds a predetermined threshold, the computer automatically switches the operating mode from normal mode to disaster mode and changes the priority or notification format of the information to be output.

[33]

[19] A road management support method as described in

[19] , characterized in that the computer collects information via a network regarding the actual occurrence of the road disaster, the results of rescue operations, the passage history of the rescue vehicles, and the analysis results obtained by analyzing the information, stores the information as learning data for an artificial intelligence model, and controls a model update process to re-learn or update the artificial intelligence model.

[34]

[19] A road management support method as described in

[19] , characterized in that the computer performs security coordination to prevent unauthorized access, prevent tampering with communication content, or perform authentication processing for information sent and received via a network between the external system, the member's mobile terminal device, or the field team member's mobile information device.

[35]

[19] A road management support method as described in

[19] , characterized in that the computer, in the event of a disaster, causes a failure of some functions due to a communication failure, power failure, or equipment failure, makes the failure of the function redundant by using another network path, an alternative server, or an alternative processing mechanism, thereby ensuring the continuity of operation of the entire system. [Effects of the Invention]

[0006] According to the present invention, by integrating and analyzing multiple pieces of information, such as information on the receipt of rescue requests from rescue requesters, information on rescue activities acquired at the scene by rescue vehicles, etc., and information reported by members, it is possible to quickly and accurately grasp the disaster situation, thereby enabling faster initial responses in rescue activities and rationalization of prioritization. In addition, by analyzing factors such as the density of rescue requests, geographical concentration, and time of occurrence, and evaluating the likelihood of a disaster occurring and the extent of its impact, AI (artificial intelligence) can be used to automate the optimal deployment plan for rescue vehicles and the selection of passable routes, thereby improving the efficiency of rescue operations and reducing the burden on on-site personnel. Furthermore, by visualizing decision-making information based on the analysis results, whether rescue is possible, recommended routes, etc. on a dashboard, and by providing a function to directly notify members and on-site personnel, it is possible to share the situation with all parties involved, improving the accuracy and speed of rescue operations. In addition, by accumulating the results of rescue operations as re-learning data for the AI ​​model and configuring it to continuously improve the accuracy of the model, it will be possible to provide highly accurate rescue support over the long term. This will enable road service operators to make rational and scientific decisions before rescue operations begin, enabling swift and optimal disaster response, in a field where previously it was difficult to grasp the situation until rescue arrived at the scene after a rescue request. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a system configuration diagram of a road disaster response support system according to the present invention. [Figure 2] FIG. 10 is a flowchart illustrating an example of a patrol flow. [Figure 3] FIG. 10 is a flowchart illustrating an example of a flow of a fixed camera. [Figure 4] FIG. 10 is a diagram illustrating an example of a patrol situation. [Figure 5] FIG. 10 is a diagram illustrating an example of an optical fiber inspection situation. [Figure 6] FIG. 10 is a diagram illustrating an example of a satellite survey situation. [Figure 7] FIG. 10 is a diagram illustrating an example of weather conditions. [Figure 8] FIG. 2 is a diagram illustrating an example of a vehicle driving situation. [Figure 9] 1 is a flowchart illustrating an example of the flow of a road disaster response support system according to the present invention. [Figure 10] FIG. 10 is a diagram showing an example of a determination criterion in a determination unit of the present invention. [Figure 11]1 is a diagram showing an example of a hardware configuration of a road disaster response support system according to the present invention. Note that the configuration diagrams and flowcharts shown in Figures 1, 9, 10, 11, etc. show examples of the present invention and do not comprehensively illustrate all of the components according to the present invention. Configurations and processes not explicitly shown in the drawings are also included as elements that can be implemented in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of the road disaster response support system of the present invention will be described with reference to the drawings. Note that the embodiment described below does not unduly limit the technical idea of ​​the present invention described in the claims. Furthermore, not all of the configurations described in this embodiment are necessarily essential components of the present invention. In addition, each individual component constituting a feature group may also be an independent invention. The system of the present invention is configured to, in the event of a disaster, comprehensively collect at least two of the following information: rescue request reception information managed by road service providers; rescue operation information obtained through rescue vehicles, drive recorders, small unmanned aerial vehicles (drones), portable information devices, etc.; and member report information provided by members; and to evaluate the possibility of a disaster occurring, its impact, and the priority of rescue operations using an AI model. Based on the results of this analysis, the system outputs information to support the planning of the deployment of equipment and personnel, including whether rescue vehicles can pass, the optimal route, whether rescue operations can be carried out and their priorities, etc. Furthermore, this information can be displayed on the dashboard in the control room and sent directly to member terminals and on-site crew terminals. In addition, this system accumulates the results of rescue operations as learning data for the AI ​​model, and by re-learning and updating the model, it is possible to continuously improve the accuracy of disaster response. In this invention, "rescue vehicle" refers to a vehicle (which may include an emergency vehicle) owned by the road service provider and used to rescue members or general vehicles, including tow trucks, service cars, loaders, and vehicles equipped with vehicle rescue equipment. "Rescue request reception information" refers to information related to a rescue request sent by a member or third party to the road service provider via telephone or app, including the requester's contact information, location information, the reason and circumstances for the need for rescue, and information about the target vehicle. "Rescue operation acquisition information" refers to information including video data, still image data, audio data, location information, and on-site environmental information acquired at the rescue operation site using a rescue vehicle, a dashcam, a small unmanned aerial vehicle (drone), a portable information device, etc. In addition, "content related to road disasters" is a concept that encompasses multiple types of information that are used for rescue activities and assessing the status of road infrastructure during disasters, such as information on receiving rescue requests, information on rescue activities obtained, member notification information, disaster information, road information, traffic information, and weather information. Paragraphs 0009 to 0069 provide basic explanations and design concepts for road disaster response, primarily aimed at road administrators (which may also be adapted and applied to inventions by road service providers), and paragraphs 0070 to 0199 provide detailed explanations of embodiments of inventions primarily for road service providers.

[0009] 1 is a system configuration diagram of a road disaster response support system 600 of the present invention. The road disaster response support system 600 includes an information acquisition unit 610 that acquires information on patrol situations, information on optical fiber investigation situations, information on satellite investigation situations, information on weather conditions, and information on vehicle travel situations, an analysis unit 620 that analyzes the patrol situations, optical fiber investigation situations, satellite investigation situations, weather conditions, and vehicle travel situations obtained from the information acquired by the information acquisition unit 610, and a decision unit 630 that comprehensively decides the need for road disaster response based on the results of the analysis by the analysis unit 620. The road disaster response support system 600 of the embodiment is communicatively connected to a patrol status providing server 100, an optical fiber investigation status providing server 200, a satellite investigation status providing server 300, a weather condition providing server 400, and a vehicle driving status providing server 500 via a network NW. Although only one vehicle Vh and one terminal device TM are shown in FIG. 1 in order to grasp the patrol situation, a plurality of vehicles Vh and terminal devices TM may be connected to the network NW. Although only one fixed camera CAM is shown in FIG. 1 to grasp the disaster situation, multiple fixed cameras CAM may be connected to the network NW. Based on the results of these analyses, the decision unit 630 determines whether road infrastructure maintenance or disaster response is necessary, and issues instructions for response processing as needed (for example, determining a repair plan or a road clearance route). Furthermore, in the present invention, the road disaster response support system 600 is configured to store information on the road clearance department, infrastructure maintenance department, improvement department, robotics department, and road service status. On the other hand, the prediction unit and information providing unit may be additionally provided in the system as needed.

[0010] The terminal device TM, fixed camera CAM, patrol status providing server 100, optical fiber investigation status providing server 200, satellite investigation status providing server 300, weather status providing server 400, vehicle driving status providing server 500, and road disaster response support system 600 communicate via a network NW. The network NW includes, for example, some or all of a WAN (Wide Area Network), LAN (Local Area Network), the Internet, a provider device, a wireless base station, a dedicated line, a satellite line, etc. The communication method is not limited to the network NW, but data can also be sent and received via a memory card. Data can also be downloaded and uploaded via the network NW. In addition, in the present invention, the function of providing information on the road service situation is configured to be provided in the road disaster response support system 600, and is acquired via the network NW through a dedicated server, terminal device, etc.

[0011] The terminal device TM is used by a user who gets into the vehicle Vh. The terminal device TM is a mobile phone such as a smartphone, a tablet terminal, or the like. The terminal device TM may be a communication-type drive recorder or a stationary in-vehicle device mounted on the vehicle Vh, or may have an image analysis function using AI (artificial intelligence).The vehicle Vh may also have an under-road cavity detection function (technology that irradiates electromagnetic waves from above the road toward below the road and estimates the locations of cavities and buried pipes from the reflected waves), or the vehicle Vh may be an under-road cavity detection vehicle. The terminal device TM has a road patrol application installed therein that cooperates with the patrol status providing server 100 . The terminal device TM has a positioning device such as a GPS (Global Positioning System) receiver, a communication device for connecting to the network NW, an input / output device such as a G sensor (acceleration sensor), a camera, and a touch panel, and a processor such as a CPU (Central Processing Unit).

[0012] 2 is a flowchart showing an example of the flow of patrol. When the terminal device TM presses a patrol start button on the road patrol app (S1), it starts collecting location information, acceleration information, video, etc. (S2). After the patrol is completed, the user presses the patrol end button in the road patrol application (S3), and the position information, acceleration information, video, etc. of the terminal device TM are transmitted to the patrol status providing server 100 (S4). The patrol status providing server 100 determines whether the road surface is uneven or not based on the measurement information transmitted from the terminal device TM, and identifies the location of the road surface that is determined to be uneven. Also, based on the transmitted video and images, it determines the state of damage to the road surface, and identifies the location of the road surface that is determined to be a risk location.

[0013] Fixed camera CAMs are installed on buildings and roadside posts and poles around areas prone to flooding, such as roads (highways, major trunk roads, roads with heavy traffic, major bus routes, roads connecting to schools, public facilities, and emergency hospitals, roads along mountains and in mountainous areas, etc.), underpasses (roads that are dug down at intersections), roads along rivers, and roads along the sea. Fixed camera CAMs include live cameras, web cameras, and network cameras that are capable of communication. The fixed camera CAM may be a communication-type drive recorder or a small unmanned aerial vehicle such as a drone, or it may be equipped with image analysis functions using AI (artificial intelligence). The fixed camera CAM has a built-in camera application that communicates with the patrol status providing server 100 . The fixed camera CAM includes a lens, an image sensor, a positioning device such as a GPS (Global Positioning System) receiver, a communication device for connecting to the network NW, and a processor such as a CPU (Central Processing Unit).

[0014] 3 is a flowchart showing an example of the flow of the fixed camera CAM. The fixed camera CAM periodically or intermittently collects road conditions (S5), and periodically or intermittently automatically transmits images, location information, date and time information, etc. to the patrol status providing server 100 (S6). The patrol status providing server 100 judges the state of damage to the road surface based on the video and images transmitted from the fixed camera CAM, and identifies the locations judged to be risky locations.

[0015] The patrol status providing server 100 provides the patrol status via the network NW to the road disaster response support system 600. The provided patrol status is information for each road, and includes some or all of the disaster status and obstacles to vehicle traffic, such as road damage, road subsidence, roadbed washout, roadway collapse, pavement damage, roadside gutter damage, road surface unevenness, cavities under the road, liquefaction, snow accumulation, snow quality, and ice on the road surface, collapsed buildings, vehicle traffic history, power outages, earthquake damage, tsunami damage, typhoon damage, eruption damage, volcanic activity damage, tornado damage, landslides, landslides, soil runoff, slope collapses, tunnel collapses, collapsed shoulders, fallen trees, falling rocks, road scouring, total bridge damage, river bank collapses, river flooding, flooding, dense fog, avalanches, blizzards, and the presence or absence of accident vehicles and stranded vehicles. FIG. 4 is a diagram showing an example of a patrol situation, in which damaged road areas 110 are displayed in black on the map.

[0016] The optical fiber investigation status providing server 200 utilizes optical fiber sensing technology that uses optical fiber as a sensor, receives backscattered light from communication optical fibers included in cables laid on roads, etc., detects vibration patterns according to the driving conditions of vehicles on the roads, etc. based on the backscattered light, and acquires the driving conditions of vehicles on the roads, etc. and the surrounding road conditions, etc. from the detected vibration patterns and a learning model (information from a camera connected to the optical fiber, etc., may also be used).In addition, by analyzing the intensity and frequency changes of minute vibrations propagating underground and continuous abnormal patterns of waveforms, it is possible to grasp the risk of underground cavities occurring and signs of ground deformation. The optical fiber inspection status providing server 200 provides the optical fiber inspection status to the road disaster response support system 600 via the network NW. The optical fiber inspection status provided is information for each road, and includes some or all of the following disaster conditions (including images of the road) and obstacles to vehicle traffic, such as vehicle traffic history, traffic volume, traffic congestion, sudden vehicle stops, traffic accidents, snow accumulation on the road surface, cavities under the road surface, collapses in tunnels, accidents, power outages, water leaks and water outages, earthquake prediction information, earthquake damage, tsunami damage, typhoon damage, eruption damage, tornado damage, and optical fiber blockages and disconnections. FIG. 5 is a diagram showing an example of an optical fiber investigation situation, in which a collapsed area 210 in the tunnel is displayed in black on the map.

[0017] The satellite survey status providing server 300 utilizes satellite remote sensing technology, which uses observations by satellites equipped with SAR (Synthetic Aperture Radar), optical sensors, microwave sensors, etc., and acquires road and vehicle conditions, etc., from the differences before and after a disaster using data (scattering intensity values, phase information, polarization information, etc.) and images (optical images, SAR images, etc.) observed by the satellite. In particular, by using time-series interference analysis such as InSAR (Interferometric SAR), it is possible to detect minute displacements such as subsidence, uplift, and tilt of the ground with high accuracy, and to estimate signs of underground cavities and the risk of their formation from deformations that appear on the ground surface. In addition, it may be a device that uses AI (artificial intelligence) analysis to compare and detect road conditions, vehicle conditions, etc. before and after a disaster, or a device that uses AI (artificial intelligence) analysis to detect and detect road conditions, vehicle conditions, etc. during a disaster. The satellite survey status providing server 300 provides the satellite survey status via the network NW to the road disaster response support system 600. The provided satellite survey status is information for each road, and includes some or all of the disaster status and obstacles to vehicle traffic, such as collapsed buildings, landslides, landslides, mudslides, slope collapses, tunnel collapses, road damage, collapsed roadways, collapsed shoulders, cavities under the road surface, fallen trees, falling rocks, total bridge damage, river breaches, river flooding, inundation, avalanches, vehicle traffic history, ground subsidence, power outages, water leaks and water outages, earthquake prediction information, earthquake damage, tsunami damage, typhoon damage, volcanic eruption damage, tornado damage, forest damage, crop damage, and the presence or absence of accidental or stranded vehicles. FIG. 6 is a diagram showing an example of a satellite survey situation, where a landslide location 310 is displayed in black on the map.

[0018] The weather condition providing server 400 provides weather conditions via the network NW to the road disaster response support system 600. The weather conditions provided are information for each region, and include some or all of the following: time, weather (clear, rainy, snowy, etc.), temperature, rainfall, snowfall, snow depth, wind speed, emergency warnings (heavy rain, strong winds, high tides, waves, heavy snow, blizzards), warnings (heavy rain, strong winds, floods, heavy snow, blizzards, etc.), information on record-breaking short-term heavy rain, landslide warning information, earthquake forecast information, earthquake information, tsunami information, eruption information, information on volcanic activity, typhoon information, tornado information, and disaster conditions (including images of roads). FIG. 7 shows an example of weather conditions, where a warning 410 and seismic intensity 420 are displayed in letters and numbers.

[0019] The vehicle driving status providing server 500 uses automobile sensing technology to acquire various data from vehicles such as connected cars, such as vehicle driving status and surrounding road conditions. In particular, it is possible to estimate abnormal behavior when a vehicle approaches a cavity based on information such as sudden braking, ABS activation, abnormal acceleration, tire spin, and bump response, making it an effective source of information for detecting risk areas caused by subsurface cavities. The vehicle travel status providing server 500 provides the vehicle travel status to the road disaster response support system 600 via the network NW. The vehicle driving conditions provided are information for each road obtained from private cars, taxis, buses, trucks, etc. (including electric vehicles), and may include some or all of the following: temperature, areas of sudden braking, skidding, tire spin, tire lock, ABS activated areas, flooded areas, and subsurface cavities from vehicle sensors, etc.; power outages, earthquake damage, tsunami damage, typhoon damage, volcanic eruption damage, tornado damage, river flooding, liquefaction, and obstacles on the road from camera footage and images, etc.; identification of collapsed buildings, landslides, collapsed slopes, collapsed tunnels, total bridge damage, damaged roads, and impassable areas from 3D data, etc.; vehicle traffic history (including standard and large vehicles), traffic volume, traffic congestion, passing speed, average speed, acceleration, and whether or not there is rain or snow from wiper operation status from probe information (including ETC2.0), etc. In addition, data may be acquired using autonomous driving technology (sensing technology for autonomous vehicles), or may be detected and interpreted using AI (artificial intelligence) analysis to detect disaster situations and vehicle obstruction information. FIG. 8 is a diagram showing an example of vehicle travel conditions, and a location 510 where no vehicle has traveled is displayed in black on the map.

[0020] The information acquisition unit 610 operating in the road disaster response support system 600 acquires the patrol status from the patrol status providing server 100, the optical fiber investigation status from the optical fiber investigation status providing server 200, the satellite investigation status from the satellite investigation status providing server 300, the weather conditions from the weather condition providing server 400, and the vehicle driving status from the vehicle driving status providing server 500 via the network NW. The patrol status provided by the patrol status providing server 100 is stored as patrol information 640. The optical fiber inspection status provided by the optical fiber inspection status providing server 200 is stored as optical fiber inspection information 650. The satellite inspection status provided by the satellite inspection status providing server 300 is stored as satellite inspection information 660. The weather conditions provided by the weather condition providing server 400 are stored as meteorological information 670. The vehicle driving status provided by the vehicle driving status providing server 500 is stored as vehicle driving information 680. Furthermore, the information acquisition unit 610 may store information related to road service status. The information related to road service status is information for each road and is mainly managed by road service providers (such as the Japan Automobile Federation) (such as information from a road service management system), and includes some or all of the following: rescue requests (date, time, location, rescue details, etc.), rescue requests due to abnormal weather (date, time, location, rescue details, etc.), rescue requests due to disasters (date, time, location, rescue details, etc.), dead battery, locked keys in the car, running out of gas, flat tires, wheels coming off or falling off, flooding or submersion, recovery from snowy or muddy roads, accidents, slips and falls, disaster or damage conditions (including photographed images of the road), towing or transportation of vehicles, removal, towing or transportation of abandoned vehicles, removal, towing or transportation of damaged vehicles, removal, towing or transportation of accident vehicles, road conditions (including photographed images of the road), traffic conditions, EV charging capabilities, vehicle inspection results, etc. The road service status is stored as road service information. The information acquired by the information acquisition unit 610 may be only a part of the patrol status, optical fiber survey status, satellite survey status, weather status, vehicle driving status, and road service status. Based on the results of an integrated analysis of this information, the decision unit 630 can be configured to determine the need for preventive maintenance of road infrastructure and the need for response in the event of a disaster (e.g., securing emergency routes, determining repair priorities, etc.), and to execute the necessary response processing.

[0021] An analysis unit 620 operating in the road disaster response support system 600 analyzes each piece of information obtained from the information acquired by the information acquisition unit 610, such as patrol information 640, optical fiber inspection information 650, satellite inspection information 660, weather information 670, vehicle travel information 680, and road service information, and stores the results as analysis results 690. The stored analysis results 690 may be configured to be viewable in the form of a map display, a list display, a time-series graph display, or the like. Furthermore, the analysis unit 620 may be configured not only to process each piece of information individually, but also to collate and compare these different types of data and make a comprehensive evaluation based on the integrated correlation. For example, it may be possible to comprehensively collate and compare at least two or more types of data from satellite data, optical fiber data, and vehicle driving data, and detect the redundancy and consistency of abnormalities at the same location from multiple perspectives such as ground surface displacement, vibration intensity, and driving abnormalities, and evaluate the risk of subsurface cavities. Furthermore, the analysis unit 620 may include an AI (artificial intelligence) model. The AI ​​(artificial intelligence) model may be configured to use a learning algorithm such as a neural network to integrate multiple pieces of sensing data as input and output a risk score (e.g., a continuous value between 0.0 and 1.0 or a risk classification category) for each location. The output score is used as auxiliary information for making decisions in road infrastructure maintenance and disaster response. It may also include a configuration in which cavity presence / absence information, cavity location information, cavity depth information, cavity shape information, etc. obtained from on-site ground surveys are input into an AI (artificial intelligence) model as learning data or update data, and processing (relearning, model update) is performed to continuously improve prediction accuracy and judgment results. For example, it is possible to use measurement data (date and time, location, seismic intensity, weather data, vibration, vehicle behavior, probe information, three-dimensional topographical data, etc.) contained in the various information (patrol information, optical fiber survey information, satellite survey information, weather information, vehicle driving information, road service information) acquired by the information acquisition unit 610 as learning data to analyze and visualize the road disaster situation and the degree of risk of infrastructure damage. Furthermore, the analysis results 690 may be configured to be utilized in cooperation with the prediction unit or improvement unit as necessary, contributing to future disaster prediction and improvement of judgment accuracy. In addition, the information analyzed by the analysis unit 620 may be configured to analyze only a portion of the patrol information 640, optical fiber inspection information 650, satellite inspection information 660, weather information 670, vehicle driving information 680, and road service information.

[0022] Furthermore, the analysis unit 620 may use a deep learning model that automatically detects abnormal signs from multiple disaster-related information sources. For example, by using LSTM (Long Short-Term Memory), abnormal patterns can be detected from time-series changes in weather information, earthquake waveforms, vehicle behavior, etc. This makes it possible to predict disaster precursors and the risk of secondary damage with high accuracy. Furthermore, a graph neural network (GNN) may be applied to analyze the road network structure and the spatial relationships between affected nodes, thereby extracting priority road clearance route candidates and routes with a high risk of damage spreading.

[0023] The analysis unit 620 may also include a process for assigning a reliability score to each data source. The reliability score is dynamically calculated based on the source (public institution / general user), observation conditions, past accuracy history, etc. The analysis unit 620 excludes or weights data below a predetermined threshold to prevent misjudgments due to inaccurate information. Furthermore, the analysis results 690 may be used to evaluate response priorities, and may be weighted and scored based on factors such as the likelihood of human casualties, the status of functional outages at evacuation centers and hospitals, and the impact of damage to lifelines, and visualized as a heat map on a map.

[0024] Furthermore, the analysis unit 620 may have a reliability score generation function that evaluates the reliability of various information used in the analysis. The reliability score generation function may be configured to score each information source acquired by the information acquisition unit 610 based on the frequency of information acquisition, past accuracy, acquisition method (automatic measurement / manual report), etc., and to supply highly reliable information to the analysis process with priority. For example, for disaster reports and resident notification information collected from social media, etc., a reliability score can be calculated taking into account the consistency of location information, the degree of agreement with the damage situation based on image analysis, past notification history, etc., and information with a score below a threshold can be excluded from analysis or corrected. The reliability score may be referred to in each process in the analysis unit 620, prediction unit, and improvement unit, and may be configured to contribute to improving information weighting and anomaly detection accuracy. Furthermore, the transparency of decision support may be increased by providing an interface (such as a reliability label display) that allows the user to explicitly check the information rating.

[0025] Furthermore, the analysis unit 620 may be provided with a citizen participation learning function that utilizes reports, posts, and feedback information from residents and users to improve the accuracy of AI (artificial intelligence) models and optimize judgment criteria. For example, the report contents (text, photos, videos, etc.) regarding damage, depressions, traffic obstructions, etc. on the road are collected together with location information and time information, and whether or not the information is consistent with the analysis result 690 or the judgment result 695 is evaluated, and accurate reports are used as training data for retraining an AI (artificial intelligence) model. In addition, the system may be configured to encourage residents to improve the quality of their posts through a feedback function (report evaluation and report correction) for false and inappropriate reports, thereby contributing to improving the overall performance of the model. This type of citizen-participation learning structure will link the flow of information from society as a whole with the AI ​​(artificial intelligence) learning platform, and is expected to lead to increased participation in the maintenance and management of public infrastructure and strengthening of local disaster prevention capabilities.

[0026] Furthermore, the analysis unit 620 may have a reliability visualization function that outputs, as accompanying information, data on which the judgment is based and the certainty (reliability) of the judgment for various judgment results by AI (artificial intelligence). In this configuration, the reason for the decision and the score are displayed side by side, for example, "This road section is recommended to be closed: reliability 87% (basis: satellite imagery + vibration anomaly + SNS report)," allowing users or administrators to confirm the transparency of the AI ​​(artificial intelligence) decision. The reliability score can be calculated using the probability output (such as softmax output) within the AI ​​(artificial intelligence) model or the consistency of the evidence (the agreement rate between multiple information sources). Furthermore, if the judgment score falls below a threshold, a note such as "Caution required" or "Further investigation recommended" can be added to help prevent overconfidence in judgment. This type of decision visualization configuration will increase social acceptance of the introduction of AI (artificial intelligence) and also contribute to improving the sense of security and satisfaction in actual operations at disaster response sites.

[0027] Furthermore, the analysis unit 620 may include a reliability evaluation mechanism based on multiple information sources. In the event of a disaster, in addition to official sensing data (satellite images, vibration sensors, vehicle behavior, etc.), near-real-time information such as reports from residents, social media posts, and patrol reports may be collected, but the reliability of this information varies. For this reason, this system may be configured to assign a predefined reliability score to each information source (e.g., Japan Meteorological Agency = high, SNS = medium, unregistered reports = low), and weight the information when inputting it into the AI ​​(artificial intelligence) model. In addition, it is also possible to evaluate the consistency (degree of consistency) and spatiotemporal consistency of content across multiple information sources, and automatically determine the reliability rank of the information (high, medium, low), or to add labels such as "needs confirmation" or "pending" to the judgment result for low-reliability information. This type of information reliability evaluation structure is also effective in preventing misjudgments at disaster sites and improving the social transparency of AI (artificial intelligence) decisions.

[0028] The road disaster response support system 600 may also be configured to cooperate with external mobility services and in-vehicle devices. For example, the system may be configured to mutually cooperate with information from mobile systems such as car navigation systems, smartphones, MaaS (Mobility as a Service) apps, self-driving vehicles, and electric vehicles (EVs) to provide road clearance information, passable routes, danger avoidance instructions, and the like in real time during a disaster. In this configuration, disaster conditions and road clearance route determination results are automatically notified to in-vehicle terminals or smartphones, and adaptive navigation instructions are possible based on the user's current location, direction of travel, driving intentions, etc. Furthermore, for autonomous vehicles, a configuration is possible in which "road avoidance commands" and "stop commands" according to road disaster conditions are directly reflected in the control system. Furthermore, API integration with MaaS service providers will enable processes such as optimizing emergency transportation methods, reconstructing routes, and adjusting traffic demand during disasters, contributing to improving disaster response capabilities across society as a whole.

[0029] The road disaster response support system 600 may also have a condition setting function for the timing and trigger of updating the AI ​​(artificial intelligence) model. The model update process may be configured to be executed automatically or semi-automatically when any of the following conditions is met: (1) When a new disaster occurs and actual damage information on the site is acquired (e.g., cavity detection results, structural damage data, image diagnosis results, etc.) (2) When the system's accuracy falls below a predetermined threshold (e.g., a continuous decline in confidence score, an increase in false positive feedback, etc.) (3) When a government or specialist agency issues a model update order (e.g., earthquake response specification revisions, regulation changes, etc.) By setting and managing such update conditions in advance, it is possible to prevent the judgment model from becoming obsolete, and to achieve continuous system maintenance and optimization of disaster response accuracy.

[0030] Furthermore, the road disaster response support system 600 may be configured to be able to dynamically change the decision rules or evaluation criteria depending on the type, scale, and damage situation of the disaster. For example, one possible configuration is to change the type of data to be targeted, the evaluation items to be prioritized (vibration intensity, flood depth, traffic blockage rate, etc.), judgment thresholds, etc. depending on the type of disaster, such as earthquake, heavy rain, landslide, etc. Furthermore, even within the same disaster, the judgment criteria may be optimized for each region, taking into account the characteristics of the affected area (urban / mountainous area, aging rate, damage to lifelines, etc.). Furthermore, by configuring the system to dynamically switch decision priorities and implementation details from the "lifesaving priority phase" to the "supply support phase" and "life restoration phase" depending on the stage of the disaster, it is possible to increase the flexibility and real-time adaptability of on-site responses.

[0031] Furthermore, the analysis unit 620 may be configured to dynamically adjust disaster response priorities according to regional characteristics. For example, in areas where facilities requiring special care, such as elderly care facilities, welfare facilities, hospitals, evacuation shelters, and elementary and junior high schools, are concentrated, the analysis unit 620 may be configured to prioritize road clearances around these facilities. It is also possible to perform a multidimensional weighting evaluation based on factors such as population density, the proportion of people vulnerable to disasters, the concentration of lifelines, and the distribution of medical resources, and automatically determine the optimal response order for each region. This enables flexible and rational decisions based not only on the physical damage situation but also on the social needs of the region.

[0032] Furthermore, the road disaster response support system 600 may be configured to handle damage to communication infrastructure or network interruptions during a disaster. For example, various information acquisition units and terminals may be configured to ensure communication without infrastructure dependency by using communication means such as a local network, mesh network, or LPWA (low-power wide area network). Furthermore, a failover configuration allows on-site terminals to autonomously continue making decisions and formulating road clearance plans even when communication with the central server is unavailable, thereby enhancing operational continuity (robustness) during a disaster.

[0033] The Road Disaster Response Support System 600 may also be equipped with a control mechanism for switching between automatic judgment and manual intervention. For example, while responses are usually handled automatically by AI (artificial intelligence), it is possible to configure the system so that expert staff or administrators can manually intervene in cases of high urgency or where there is a high degree of uncertainty. This creates a safety net against the risk of misjudgment by AI (artificial intelligence), improving reliability and flexibility in disaster response. Records of manual intervention are also stored in the system, allowing for a configuration that can contribute to future model improvements.

[0034] Furthermore, the road disaster response support system 600 may be configured to perform specialized processing according to the type of disaster. For example, it may be configured to change the evaluation criteria and weightings used in analysis processing, decision processing, and road clearance route selection, taking into account the different damage characteristics, progression speed, and impact range for each disaster type, such as earthquakes, heavy rain, volcanic eruptions, and tsunamis. This enables optimal decisions to be made for each disaster, improving response accuracy. Specifically, it may be possible to implement AI (artificial intelligence) model selection and switching processing that reflects disaster characteristics, such as prioritizing shaking and ground movement during earthquakes and flood depth and drainage capacity during heavy rain.

[0035] The road disaster response support system 600 may also be configured to switch judgment criteria and processing methods in stages according to the chronological phases of a disaster (before the disaster, immediately after the disaster, emergency response period, and full-scale restoration period). For example, it may prioritize rule-based processing that emphasizes speed immediately after the disaster occurs, and switch to AI (artificial intelligence) analysis that emphasizes accuracy when the situation calms down, thereby achieving optimal judgment according to the time series. The configuration may also include an RNN model (Risk Need Responsibility model) using time series data and event trigger judgment based on the disaster progression flow.

[0036] The road disaster response support system 600 may also have a hybrid AI (artificial intelligence) configuration. For example, by combining disaster response decisions based on an AI (artificial intelligence) model with explicit rule-based (IF-THEN) decisions, the explainability of the output from the AI ​​(artificial intelligence) model and the basis for the decision can be clarified. In particular, during large-scale disasters, it is important for residents and commanders to understand "why a particular route was selected," so the system may be implemented to present the decision results with an explanation. It may also include a configuration that utilizes LLM (large-scale language model) to automatically generate explanations in natural language for the reasons for route selection.

[0037] The road disaster response support system 600 may also be configured to use live footage of the scene captured by patrol vehicles, drones, fixed cameras, surveillance cameras, robots, etc., and perform image recognition and anomaly detection processing using AI (artificial intelligence). For example, AI (artificial intelligence) can automatically detect visual abnormalities in the footage, such as debris piles, flooding, and cracks in the ground, and execute control processing to increase the priority response level of the relevant location. This enables real-time understanding of the disaster situation and support for judgment without relying on visual inspection, improving the accuracy of road clearance and support vehicle guidance.

[0038] Furthermore, the road disaster response support system 600 may be configured to be capable of disaster response training and simulations in peacetime. For example, it may be configured to input past disaster data and hypothetical disaster scenarios, perform hypothetical judgments using the prediction unit and analysis unit 620, and then, based on the results, execute simulated road clearance plans, support route generation, and confirmation of material transportation plans. This enables practical training before a disaster occurs, improving the ability to respond quickly and accurately in the event of an actual disaster.

[0039] Furthermore, the Road Disaster Response Support System 600 may be configured to process disaster information in real time using not only cloud processing but also edge AI (artificial intelligence) implemented on local terminals. For example, patrol cars, drones, robots, etc. deployed at disaster sites may perform on-site processing even in environments where cloud communication is difficult, and perform local judgment, notification, and control. This makes it possible to provide a certain level of judgment support, road clearance judgment, and danger avoidance even when communication is interrupted, achieving highly resilient disaster response.

[0040] The analysis unit 620 may also be equipped with a triage processing function that assumes a situation in which a large amount of disaster-related information is concentrated at once and prioritizes it according to urgency and importance. For example, when a large number of disaster reports and sensor data are input simultaneously, the system can be configured to prioritize disaster areas directly connected to life and daily infrastructure, and to appropriately allocate resources and determine whether to clear roads, thereby avoiding delays in decision-making and excessive or insufficient responses. The AI ​​(artificial intelligence) model can calculate a priority score based on factors such as the extent of damage, surrounding conditions, and the reliability of the communication source, and determine the processing order based on that score.

[0041] Furthermore, the road disaster response support system 600 may have a hybrid configuration that flexibly uses both cloud and local processing. For example, in situations where network bandwidth is limited, such as immediately after a disaster, important decision-making processes may be executed on local terminals or base servers, and then synchronized and integrated with analysis on the cloud once the network is restored. This achieves both continuity of processing during a disaster and overall optimization. An architecture configuration may also be adopted in which the basis for decisions and processing results are recorded and shared, contributing to subsequent analysis and improvement processes.

[0042] The decision unit 630 operating in the road disaster response support system 600 determines the need for road disaster response and road infrastructure maintenance in an integrated and comprehensive manner based on some or all of the analysis results 690 of various information (including patrol information, optical fiber survey information, satellite survey information, weather information, vehicle driving information, and road service information) analyzed by the analysis unit 620, and stores the determination result 695. The determination result 695 may include determination criteria that reflect the risk score threshold, correlation patterns between analytical data, consistency with ground surveys, etc. The determination result 695 may be configured to be visualized on a map display, a list display, a time series graph display, or a dashboard. The decision unit 630 may also have a decision support function using an AI (artificial intelligence) model, and may be configured to determine the priority of maintenance, the urgency of disaster response, etc. based on statistical threshold decision, rule-based decision, or a predictive model using machine learning. In this case, the decision execution method may be configured as fully automatic processing, semi-automatic processing requiring confirmation by an operator, or a proposal-based support mode. Furthermore, the determination unit 630 may be configured to function as a trigger for executing disaster response support processing, including proposing repair plans, determining road clearance routes, recommending emergency vehicle routes, determining traffic restrictions, etc., as necessary. This enables automatic or semi-automatic disaster response support linked with the analysis results 690. Additionally, the decision unit 630 may be configured to cooperate with the road clearance unit or the robotics unit to formulate a road clearance implementation plan or give instructions for road clearance work by robots based on the determination result 695. This links determination and execution, realizing a fast and efficient disaster response. Furthermore, the judgment results 695 and the analysis results 690 may be used in the improvement department to retrain the AI ​​(artificial intelligence) model and update the judgment criteria, and may be combined with past history data and future scenario data to be reflected in the prediction department's prediction of future disaster risks and the development of advance plans. Furthermore, the road disaster response support system 600 may include an information providing unit that provides to an external party a part or all of the judgment result 695 and the analysis result 690. This information providing unit has the effect of enabling road disaster response policies and countermeasure information to be quickly disseminated and shared with administrative agencies, related businesses, general residents, etc. In addition, the decision unit 630 may be configured to automatically generate an explanation in natural language using a large-scale language model (LLM) for the judgment made by AI (artificial intelligence), thereby increasing the transparency and explainability of the basis for the judgment. Furthermore, the determination result 695 may be configured to be output in a foreign language (such as English or Chinese) through a multilingual translation configuration, and may be used to notify or explain to foreign users.

[0043] FIG. 9 is a flowchart showing an example of the flow of the road disaster response support system 600. The information acquisition unit 610 periodically acquires (e.g., every few minutes) information on patrol status from the patrol status providing server 100 (S10). The information acquisition unit 610 periodically acquires (e.g., every few minutes) information on optical fiber inspection status from the optical fiber inspection status providing server 200 (S11). The information acquisition unit 610 periodically acquires (e.g., every few minutes) information on satellite inspection status from the satellite inspection status providing server 300 (S12). The information acquisition unit 610 periodically acquires (e.g., every few minutes) information on weather conditions from the weather condition providing server 400 (S13). The information acquisition unit 610 periodically acquires (e.g., every few minutes) information on vehicle driving status from the vehicle driving status providing server 500 (S14). The analysis unit 620 then extracts road damage locations and the like from the patrol information 640 (S15). The analysis unit 620 extracts travel history and the like from the optical fiber inspection information 650 (S16). The analysis unit 620 extracts landslide locations and the like from the satellite inspection information 660 (S17). The analysis unit 620 extracts earthquake and tsunami information and the like from the weather information 670 (S18). The analysis unit 620 extracts impassable areas and the like from the vehicle travel information 680 (S19). Next, based on the above analysis results, the decision unit 630 comprehensively determines the necessity of road disaster response, and makes a decision (S20) to execute response processing (for example, determining repair plans and road clearance routes, etc.) as necessary. Furthermore, the road disaster response support system 600 may be equipped with information from road users and residents using SNS (Social Networking Service) (disaster information, victim information, relief information, recovery information, etc.), information from government (police, fire department, Self-Defense Forces, etc.), infrastructure operators (communications, electricity, gas, water, sewerage, etc.), transportation operators (railways, buses, ferries, airplanes, etc.), construction and civil engineering operators (including construction industry associations), delivery companies, tourism operators (inns, hotels, tourist facilities, roadside stations, etc.), designated public institutions (Disaster Countermeasures Basic Act) (disaster information, victim information, relief information, recovery information, etc.), and information from the government's Emergency Disaster Countermeasures Headquarters and Emergency Disaster Countermeasures Headquarters. It should be noted that FIG. 9 shows an example of a typical processing flow, and the present invention is not limited to this.

[0044] 10 is a diagram showing an example of the determination criteria in the determination unit 630. The determination unit 630 can determine the necessity of road disaster response when triggered by events such as the occurrence of a tsunami (element 1) 631, a slope collapse causing an optical fiber disconnection (element 2) 632, road damage and collapsed buildings resulting in no vehicle traffic (element 3) 633, a heavy rain warning being issued and landslides causing tires to spin, preventing vehicles from moving forward and causing severe traffic congestion (element 4) 634, or a heavy snow warning being issued and snow having accumulated on the road surface causing the ABS to activate, causing severe traffic congestion with many stranded vehicles (element 5) 635. Furthermore, with regard to some or all of the judgment result 695 determined by the decision unit 630, the analysis result 690, and the various information acquired by the information acquisition unit (patrol information, optical fiber survey information, satellite survey information, weather information, vehicle driving information, road service information), etc., through the information provision unit, etc., the system may be provided with a function to notify road administrators by email, a function to provide data to a road information board system, a function to provide data to a road restoration visualization map (a map on a web site that centrally displays road restoration status, major affected areas and damage status, road traffic restrictions, inter-city travel time, vehicle speed data, vehicle traffic history, population mesh data, etc.), a function to provide data to a car navigation system, a function to provide data to an automated driving system, a function to provide data to MaaS (Mobility as a Service), a function to provide information to government agencies (police, fire departments, Self-Defense Forces, etc.) and the media, and a function to disclose information to road users and residents (websites, smartphone apps, etc.), and does not necessarily have to go through the information provision unit. Examples of the information disclosure function to road users and residents are as follows, but are not limited to these. A road disaster response support system characterized by transmitting one or more pieces of information acquired by an information acquisition unit, or the results of analysis by an analysis unit, or the need for road disaster response determined by a decision unit, or a road clearance implementation plan formulated by a road clearance unit, or the recovery status by a robotics unit, or the need for road disaster response predicted by a prediction unit, to a mobile terminal device (such as a mobile phone, smartphone, tablet device, laptop computer, game console, etc.) or a fixed terminal device (such as a desktop computer, smart TV, set-top box, digital signage, kiosk terminal, car navigation system, car display audio, etc.). It should be noted that FIG. 10 shows an example of a typical determination criterion, and the present invention is not limited to this.

[0045] The road disaster response support system 600 may include an improvement unit that continuously improves the analysis results 690 (including the analysis method) obtained by the analysis unit 620, the judgment results 695 output by the decision unit 630, and some or all of the judgment criteria. The improvement unit aims to improve the accuracy of the analysis and judgment processes and reduce erroneous judgments by utilizing disaster-related data (images, numerical data, simulation results, etc.) obtained from external sources. The improvement unit can also cooperate with the infrastructure maintenance unit and the road clearance unit, and can optimize the improvement targets for each process (cavity risk assessment, repair judgment, road clearance route determination, etc.). An example of the improvement process is a processing configuration in which hypothesis data, verification data, future prediction data, etc. related to a disaster are input, and after referring to the history of past judgment results 695 and analysis results 690, the improvement unit performs re-evaluation and relearning using methods such as statistical analysis and machine learning, and the results are fed back to the existing model to improve the accuracy of judgment. The improvement unit may have an analysis function using AI (artificial intelligence) and perform model re-learning processing for image recognition and risk score calculation. For example, the improvement unit inputs image data generated from patrol information, optical fiber survey information, satellite survey information, weather information, vehicle driving information, and road service information acquired by the information acquisition unit 610, as well as various associated sensing data (position information, vibration, temperature, speed, topographical information, etc.), predicts and outputs disaster situations, and uses the corrected and supplemented results to tune the AI ​​(artificial intelligence) model and judgment criteria. In addition, the improvement department can use information on the presence or absence of cavities, cavity location information, cavity depth information, or cavity shape information obtained from on-site ground surveys as "correct data (teaching data)" and, through re-training of the AI ​​(artificial intelligence) model, improve the predictive accuracy of cavity risk assessments and continuously improve the results of infrastructure maintenance decisions. The improvement process may be performed by the improvement unit alone, or may be configured to operate in cooperation with an infrastructure maintenance unit or a road clearance unit. The improvement unit may also be configured to work with the prediction unit as needed to improve the model or reset the criteria based on the disaster prediction results.

[0046] Furthermore, the improvement unit may be configured to flexibly select and apply different decision logic depending on the type and occurrence of the disaster in cooperation with the analysis unit 620 and the road clearance unit. For example, the improvement unit dynamically adapts to the type of disaster, such as adopting analysis logic that emphasizes the vibration frequency of structures in the case of earthquake disasters, and priority decision logic based on flood predictions and road flooding height in the case of flood disasters. This enables flexible and accurate decisions to be made in accordance with the actual situation of the disaster.

[0047] The improvement unit may also be configured to sequentially collect and learn the results of various disaster responses (road clearance record, passability, restoration speed, etc.), and use feedback learning to improve the accuracy of future decisions and implementation plans. In this case, linking the information reliability evaluation results (score) prevents bias in learning due to erroneous information. Furthermore, the improvement unit may have a function to explicitly store model update conditions (deterioration in accuracy, change in disaster type, occurrence of new data, etc.) and automatically update the model when specified conditions are met.

[0048] Furthermore, the improvement unit may be configured to sequentially acquire information such as obstacle removal work performed by the robotic equipment by the road clearance unit, passability information on the road clearance route, and on-site restoration progress logs, and use this information to retrain the AI ​​(artificial intelligence) model used by the analysis unit 620. This realizes optimization of robotics control and improvement of environmental adaptability, enabling continuous improvement of road clearance processing accuracy and initial response capabilities in the next disaster. In addition, the improvement unit may be configured to accumulate on-site environmental sensor information (vibration, collision, temperature, terrain change, etc.) acquired during robotics work as training data and use it for model performance evaluation and tuning.

[0049] The road disaster response support system 600 may include a prediction unit that predicts future disaster occurrences and road damage risks in advance by utilizing the history of previously acquired analysis results 690 and judgment results 695. The prediction unit can input and analyze various time-series data related to disasters (actual data, future scenario data, weather forecast data, etc.) and output the need for future road disaster response quantitatively or probabilistically. This will enable road managers to plan and implement advance preparations, response plans, and training plans in preparation for the risk of disasters during peacetime, thereby speeding up and streamlining initial responses when a disaster actually occurs. One example of prediction processing is a configuration in which hypothesis data, verification data, training data, and future prediction data (such as expected patterns of earthquakes or heavy rain disasters that may occur once every few decades) are input into the prediction section, and this is compared with existing analysis history and judgment results to simulate in advance the scope of impact and necessary responses in the event of a disaster. The prediction unit may be equipped with a prediction function using AI (artificial intelligence), and may be configured to use a prediction model that has learned multiple input factors, such as weather conditions, topography, past disaster records, and road structure, to preliminarily identify areas where it is difficult to secure road clearance routes and risk areas that may hinder the passage of emergency vehicles. Furthermore, the prediction results may be utilized in cooperation with the analysis department and improvement department, and may be fed back to the infrastructure maintenance department and road clearance department in formulating advance plans as needed.

[0050] Furthermore, the prediction unit may be configured to be able to evaluate not only future disaster risks but also the risk of secondary damage caused by infrastructure aging and insufficient maintenance. For example, the prediction unit may take into account past repair history and infrastructure deterioration indexes to predict areas where damage may expand and the risk of chain collapses that may occur in the future, and reflect this in advance repair and road clearance plans.

[0051] The prediction unit may also be equipped with a scenario simulation function, which performs multi-condition analysis using multiple disaster occurrence conditions (rainfall intensity, location of the epicenter, time of occurrence, etc.) as variables, and may be able to compare and consider the optimal initial response, traffic route, emergency supply transportation route, etc. for each case. In this case, it may be possible to link with a human-in-the-loop decision-making support function to configure a proposal mechanism that assumes the intervention of a manager's judgment.

[0052] The Road Disaster Response Support System 600 functions effectively by using one or more pieces of information from among patrol status, optical fiber survey status, satellite survey status, weather conditions, vehicle driving status, and road service status, and in particular, by combining two or more pieces of information, mutually complementary analysis becomes possible, realizing more accurate situational understanding and decision support. For example, by understanding wide-area surface movements through satellite surveys, detecting local underground vibrations through optical fiber surveys, and acquiring driving records and abnormal behavior through vehicle driving conditions, it becomes possible to achieve both wide-area monitoring and local detection. This will create a multi-layered decision-making platform, from predictive monitoring in peacetime to emergency response decisions in the event of a disaster. In addition, by conducting an integrated analysis that comprehensively compares and collates these multiple pieces of information, it goes beyond simply listing information and enables the following advanced decision-making processes: (1) Improved accuracy through matching of image data with non-image data: For example, if road damage is detected through image analysis, it can be compared with the corresponding optical fiber displacement and vehicle vibration history to reduce false positives and improve the reliability of disaster assessment. (2) Enhanced situational awareness based on multi-perspective information: Even in situations where detection is difficult using a single sensor, such as at night or in bad weather, it is possible to understand the damage situation in a timely and spatially complementary manner by using other information sources (satellite, driving, weather, etc.). (3) Improved rationality and responsiveness of decisions: Through integrated matching processing based on diverse sensing information and structural analysis using AI (artificial intelligence), risk assessment of road infrastructure, prioritization of disaster response, and determination of road clearance routes can be carried out quickly and rationally. In this way, this system will contribute to minimizing damage and speeding up the recovery of disaster-stricken areas by achieving both a faster initial response when a disaster occurs and more advanced preventive maintenance during peacetime.

[0053] Another embodiment of the present invention may employ a simple configuration for acquiring and analyzing information in stages. In this embodiment, a preliminary determination is first made of the occurrence and severity of a road disaster based on information about weather conditions and information about patrol status. Then, only if a road disaster is determined to be severe, additional information on at least one of vehicle driving status, optical fiber survey status, satellite survey status, and road service status is acquired, and detailed analysis and disaster response decisions are made. This configuration allows for practical disaster response support while reducing system costs and load. In this configuration, the information acquisition unit 610 first acquires information on weather conditions and patrol situations, and the analysis unit evaluates the occurrence and severity of road disasters (for example, earthquakes of seismic intensity 6 or higher, widespread wind and flood damage, snow damage, landslides, etc.) based on this information. If the evaluation result exceeds a predetermined threshold, the information acquisition unit 610 additionally acquires other sensing information, and the analysis unit 620 reanalyzes this information, enabling more advanced disaster response decisions. This allows for efficient system operation through step-by-step information utilization. Furthermore, in the processing of this embodiment, the decision unit 630 may determine whether or not a disaster response is necessary and the response policy, as in the normal configuration, and may perform emergency response, notification processing, etc. as necessary. Furthermore, this tiered configuration can also be applied to specific operation modes and simple implementation forms as an auxiliary configuration for the multiple sensing integrated analysis processing, which is the main configuration.

[0054] The road disaster response support system 600 may be provided with a road clearance unit that registers a road clearance plan that has been formulated in advance and determines a road clearance route based on the road clearance plan and acquired information when a disaster occurs. By providing the road disaster response support system 600 with a road clearance unit, it is possible to obtain the effect of quickly clearing roads in the event of a disaster. In typical disasters, the process is emergency restoration followed by full restoration. However, in large-scale disasters, emergency restoration (road clearance) must be carried out before emergency restoration. Road clearance involves quickly removing a minimum amount of rubble and repairing uneven sections to ensure a rescue route, allowing emergency vehicles to pass through for rescue and rescue operations, emergency supply support, and restoration. Road administrators develop road clearance plans in advance, including road clearance bases (bases for support units, disaster prevention centers such as storage areas for supplies and equipment), road clearance routes (wide-area travel routes, access routes, and routes within the affected area), and specific action plans (timelines). A timeline is an action plan that coordinates relevant organizations in the event of a disaster, organizing and sharing in advance a chronological order of who will do what and when. An example of the road clearance unit in the road disaster response support system 600 is a configuration that registers a road clearance plan that was formulated in advance before or after a disaster (it can be registered before or after the disaster), determines a road clearance route in the event of a disaster based on multiple disaster / disaster / traffic related data acquired by the information acquisition unit 610 or the results of an integrated analysis by the analysis unit 620, and formulates an optimized road clearance implementation plan based on that decision. The road clearance plan can be registered by registering plan information entered in advance by an administrator, or by having the computer automatically register road clearance plans obtained from an external system. This allows for both the flexibility of manual input and the speed of automatic processing. The road clearance unit may also have an analysis function and a route determination function using AI (artificial intelligence).For example, two or more pieces of information among patrol information, optical fiber survey information, satellite survey information, weather information, vehicle driving information, and road service information acquired by the information acquisition unit 610, or image, sensor, and three-dimensional topographical data based on these pieces of information, may be input into a machine-learned model, and the road disaster situation may be output, supplemented, and corrected, and then a process may be performed to dynamically determine a road clearance route. Furthermore, the determination of the road clearance route may be configured to select the optimal route in accordance with the disaster situation from multiple candidate routes that avoid high-risk points that should be avoided. The road clearance route and road clearance implementation plan determined by the road clearance unit may be notified to the road administrator via a management terminal or an external server, and may be automatically reflected in coordination with restoration work and traffic regulation instructions. In addition, the determination process may be configured to complement or correct the route determination process by the road clearance unit by referring to on-site information acquired by the robotics unit. Furthermore, the road clearance unit may be configured to cooperate with the analysis unit 620, improvement unit, prediction unit, or infrastructure maintenance unit as necessary, to improve the accuracy of road clearance routes in the event of a disaster and to contribute to dynamic re-planning processing.

[0055] Furthermore, the road clearance unit may have a function to comprehensively evaluate past disaster history, current damage status, and the functional status of evacuation, medical, and logistics infrastructure, and automatically generate a road clearance order based on the priority of rescue activities. For example, it may give top priority to areas with the greatest degree of damage and the highest possibility of saving lives, while also performing scoring that takes into account accessibility to important logistics centers and medical institutions, and determine the priority of each segment to be cleared. The score may be configured to be updated in real time based on dynamic conditions (weather, traffic congestion, aftershock risk, etc.).

[0056] The road clearance department may also be equipped with a multi-criteria optimization function that automatically generates multiple route candidates, evaluates each candidate from the perspectives of cost, time, and safety, and determines the optimal route. In this case, a human-in-the-loop configuration may be adopted, in which the route proposals proposed by AI (artificial intelligence) are manually reviewed or feedback is received and the model is updated accordingly. The determined road clearance implementation plan is notified via a management terminal or external server and used to share information and provide work instructions with related organizations. The department may also be configured to work with the robotics department, analysis department 620, and improvement department to dynamically re-plan the route, reflecting information acquired on-site.

[0057] Furthermore, the road disaster response support system 600 may be provided with a security configuration to prepare for communication failures and cyber attacks when a disaster occurs. This configuration employs a "zero trust architecture" that implements multiple layers of user authentication, communication encryption, access control, etc., thereby enhancing the security resilience of the entire system. In addition, encrypted communication and mutual authentication are also implemented between each subsystem, minimizing the risk of unauthorized access and information tampering in the event of a disaster. Furthermore, in preparation for a main server failure or network disconnection, a failover configuration (automatic switching to a redundant system) or a configuration with an alternative processing function on a local terminal may be used. For example, even if instructions from the cloud server cannot be received, the local device can be configured to autonomously present and execute response policies using pre-downloaded road clearance plans and AI (artificial intelligence) models. With this enhanced security and resilience configuration, the Road Disaster Response Support System 600 ensures high availability and safety even in the event of a large-scale disaster, contributing to improved reliability for full-scale adoption by local governments and public institutions.

[0058] Furthermore, the road disaster response support system 600 may be configured to perform clustering processing according to the characteristics of the affected municipality or region, and to perform judgment processing that is individually optimized for each region. For example, by using regional characteristic data such as population density, topography, traffic infrastructure density, and disaster history to cluster multiple similar municipalities and apply different models and priority evaluation criteria to each cluster, it becomes possible to respond to disasters in a flexible manner that is not uniform.

[0059] Furthermore, the road clearance unit may be provided with a cooperation configuration for carrying out road clearance work at disaster sites using robotic equipment (autonomous heavy machinery, remotely operated removal devices, etc.). The road clearance unit cooperates with the analysis unit 620 or the improvement unit to determine the type, size, removal means, etc. of obstacles on the road clearance route, and sends work instruction data according to the determination results to the robotic equipment, thereby automating or semi-automating on-site work. Furthermore, work performance information (processing time, obstacle processing history, on-site image and sensor information, etc.) fed back from the robotics equipment can be sent to the analysis unit 620 or improvement unit and reflected in route decisions, work estimates, and work model selection for the next disaster response. This allows for a link between decisions made by AI (artificial intelligence) and robotics as an execution unit, significantly improving responsiveness and safety in disaster response.

[0060] The road disaster response support system 600 may include a robotics unit that uses AI (artificial intelligence) and robotics technology to use robots (mainly disaster response robots) to perform road clearance work. The robots use AI (artificial intelligence) to determine which roads should be prioritized for clearance, specify the road clearance route, and perform road clearance work using robotics technology. When performing road clearance work, the robots use AI (artificial intelligence) to perform optimal route analysis based on a pre-established road clearance plan registered in the road clearance unit or a road clearance implementation plan established by the road clearance unit, and information acquired by the robotics unit (disaster and damage situation, weather conditions, road conditions, traffic conditions, impassable conditions, rescue situation, recovery situation, obstacle information, topographical information, road clearance progress information, latest on-site information, etc.) (The robots do not necessarily have to be autonomous robots). The Robotics Department will achieve the following benefits: By utilizing autonomous robots, work can be carried out quickly without relying on human labor. Furthermore, by using robots to carry out autonomous work, the dispatch of workers to dangerous areas can be minimized. Furthermore, the coordination of large heavy machinery, small robots, drones, etc. will enable efficient obstacle removal, etc. An example embodiment of the robotics section in the road disaster response support system 600 is as follows, but is not limited to this (each robot is connected to a network NW). A road disaster response support system (including road management methods) characterized in that the Robotics Department uses artificial intelligence analysis and robotics technology to carry out road clearance work using disaster response robots (large heavy machinery, autonomous heavy machinery, small robots, humanoid robots, four-legged robots, snake-type robots, multi-legged robots, earthworm-type robots, transforming robots, multi-joint robots, crawler robots, autonomous excavation robots, small unmanned flying robots, underwater search robots, rescue robots, etc.) based on a pre-established road clearance plan (a road clearance plan registered with the Road Clearance Department) or a road clearance implementation plan. Examples of robotics technology (including disaster response robots) include, but are not limited to, the following: Remotely or autonomously controlling autonomous heavy machinery (such as bulldozers and excavators) to remove obstacles and repair uneven surfaces; Working in conjunction with radio-controlled debris removal robots to remove small amounts of debris; Utilizing four-legged robots or drones to assist in reconnaissance of disaster areas and light-duty removal of obstacles; and using AI (artificial intelligence) to analyze the progress of road clearance in real time and automatically adjust optimal work instructions for the robots. Additionally, integrated control of multiple different robots (such as autonomous heavy machinery, small robots, and drones) to optimally allocate tasks. Examples of AI (artificial intelligence) include, but are not limited to: Route optimization AI for calculating road clearance routes and determining priorities (Dijkstra algorithm, reinforcement learning, multi-agent, etc.); Image recognition AI for identifying obstacles using drone and robot sensors and generating 3D maps (convolutional neural networks, PointNet, etc.); Robotics control AI for controlling autonomous heavy machinery, collaborative work by small robots, automatic obstacle avoidance and path planning (imitation learning, reinforcement learning, deep reinforcement learning, multi-agent, simultaneous localization and mapping, etc.); Dynamic route update AI (machine learning, long short-term memory, etc.), and work monitoring by AI (convolutional neural networks, long short-term memory, Transformer, etc.). Examples of input and output data in robotics technology and AI (artificial intelligence) analysis include, but are not limited to, the following: Route optimization AI (artificial intelligence): Input data (road network data, obstacle data, real-time traffic data, priority route information, weather and parcel number data, etc.) → Output data (optimal road clearance routes, emergency routes, work instruction lists, etc.). Image recognition AI (artificial intelligence): Input data (drone footage, LiDAR point cloud data, past disaster data, etc.) → Output data (obstacle maps, obstacle type determination, work priority maps, etc.). Robotics control AI (artificial intelligence): Input data (work area maps, obstacle information, robot status data, terrain data, etc.) → Output data (robot work plans, movement route instructions, obstacle removal operations, etc.). Work monitoring AI (artificial intelligence): Input data (work video data, robot work logs, weather information, etc.) → Output data (progress reports, anomaly detection alerts, work optimization instructions, etc.). By utilizing large-scale language models, road clearance plans, road clearance implementation plans, and road clearance operations can be continuously improved regardless of the type of language. This is particularly effective for understanding road clearance plans formulated in advance, learning disaster countermeasures using vast amounts of data on the Internet, and making real-time decisions in response to disasters. Examples of the use of large-scale language models include, but are not limited to, the following: complementing and optimizing road clearance plans and road clearance implementation plans, learning from global disaster countermeasure data on the Internet, real-time support for robots, and real-time use of disaster data. The robotics unit may operate in cooperation with the analysis unit 620, improvement unit, prediction unit, and road clearance unit, and may include a configuration that dynamically updates the target areas and priorities for road clearance work based on disaster risk information and judgment results provided by each unit. Furthermore, the robotics unit may cooperate with the infrastructure maintenance unit as needed to coordinate with actual restoration work carried out immediately after disaster response and to provide support for regular infrastructure repairs. The robot types listed above are merely examples and are not limited to these. Other types of robots may be used as appropriate depending on the purpose of disaster response and the environment in which they are used.

[0061] The road disaster response support system 600 may include an infrastructure maintenance department. In this specification, "information related to infrastructure integrity" means information related to maintaining the functional or physical integrity of social infrastructure, such as structural abnormalities, cavity risk, subsidence tendency, cracks, abnormal vibrations, signs of deterioration, and other information. The Infrastructure Maintenance Department is responsible for evaluating the health of road infrastructure and making maintenance decisions during peacetime, and in the event of a disaster, it is equipped with a system that links the results of these decisions with disaster response processing, thereby contributing to the compatibility of maintenance and initial response. The infrastructure maintenance unit may be configured to calculate a subsurface cavity risk score using an AI (artificial intelligence) model based on at least two of the satellite data, optical fiber data, and vehicle driving data acquired by the information acquisition unit, thereby enabling quantitative extraction of locations where subsurface cavity formation is a concern and supporting prioritization of infrastructure inspections and repairs. Additionally, for locations that are judged to have a high risk of cavities, on-site ground surveys (for example, underground radar surveys, vibration measurements, camera photography, etc.) are conducted, and the results (presence, location, depth, shape, etc. of cavities) are re-input as learning data or update data for the AI ​​(artificial intelligence) model, thereby enabling continuous improvement in the prediction accuracy of the AI ​​(artificial intelligence) model or infrastructure maintenance decisions. Furthermore, the system may be equipped with XAI (Explainable AI) technology that visualizes the output risk score and the basis for anomaly assessment, and may be configured to prioritize correct data acquisition through an active learning strategy or to use augmentation processing of learning data using GAN (Generative Inverse Network), etc. This will enable improvements in model accuracy and learning efficiency. This configuration will enable road managers to make accurate and rational repair decisions based on infrastructure assessment results and on-site survey information based on AI (artificial intelligence), contributing to the optimization of maintenance costs and the prevention of accidents. The infrastructure maintenance unit may operate in cooperation with the analysis unit 620 or the improvement unit, and may be configured to update and optimize cavity risk assessment based on analysis results and judgment results. Furthermore, the infrastructure maintenance unit may be configured to cooperate with the prediction unit, road clearance unit, and robotics unit as necessary to support actual restoration work after disaster response and ongoing infrastructure maintenance.

[0062] Furthermore, the road disaster response support system 600 may have a function for controlling cooperation with multiple robotics devices (unmanned vehicles, unmanned heavy machinery, drones, etc.) deployed at the disaster site. In this configuration, it is possible to switch between remote control mode and autonomous operation mode for each robotic device. For example, at the initial stage of a disaster, the device can be deployed within a safe range by remote control, and once stable operation has been confirmed, it can be switched to autonomous operation mode depending on the situation on site. In addition, in cooperation with the analysis unit 620 or the road clearance unit, missions based on the disaster situation (e.g., removing obstacles, taking images, securing access routes) may be automatically assigned to robotic devices, allowing multiple machines to work in parallel and cooperatively. Furthermore, by integrating and analyzing sensing information (images, three-dimensional terrain, vibrations, obstacle detection, etc.) obtained from each device in real time and providing feedback to the behavior of other units, a cooperative control mechanism can be installed, enabling efficient and safe disaster response operations. This type of robotics collaborative control configuration contributes to reducing human risks, improving work efficiency, and expanding the area that can be covered at disaster sites.

[0063] Furthermore, the road disaster response support system 600 may also have an emergency supply transportation support function. For example, it may be configured to link roads to be cleared with the logistics network (medical supplies, food, water, fuel, etc.) and prioritize roads necessary for emergency vehicle traffic for restoration. It may also be possible to link with information on relief supply collection and distribution centers and perform road selection processing that maximizes logistics efficiency. It may also be implemented with processing that optimizes the logistics network during a disaster using AI (artificial intelligence) judgment that takes into account transport schedules, traffic history, road damage levels, etc.

[0064] The road disaster response support system 600 may also have a user interface configuration that visually presents output information such as the analysis results 690 and the judgment results 695 in a variety of output formats. Specifically, information such as response priorities, road reopening routes, and the extent of the disaster impact may be output in the form of a map display using a geographic information system (GIS), augmented reality (AR) navigation, or a list format. This allows for optimal information presentation according to the situation to a variety of users, such as field workers, local government officials, and command headquarters, improving the effectiveness of decision support.

[0065] The road disaster response support system 600 according to the present invention may include, in addition to the integrated analysis configuration using the AI ​​(artificial intelligence) model described above, analysis processing using non-AI methods such as statistical analysis, threshold comparison, rule-based inference, etc., without being limited to AI (artificial intelligence) models. This enables flexible configuration selection according to the operating environment and optimization from the perspectives of real-time performance and processing load. In addition, the system may be configured to switch between integrated analysis using these non-AI methods and analytical processing using an AI (artificial intelligence) model depending on the application, system configuration, and operating conditions. Examples include, but are not limited to, the following: An information acquisition unit that acquires at least two of information on satellite survey status, information on optical fiber survey status, and information on vehicle driving status, an analysis unit that performs an integrated analysis of the information by statistical analysis, threshold comparison, or rule-based inference, and a decision unit that determines whether road infrastructure maintenance or disaster response is required based on the analysis results.

[0066] Furthermore, the road disaster response support system 600 according to the present invention may include a configuration for switching the operation policy between a normal operation mode and a disaster operation mode. In normal times, the main purpose is to identify predictive abnormalities in road infrastructure, assess cavity risks, and make decisions about regular maintenance. However, in the event of a disaster, the system will switch to an operational mode where the main purpose is to secure emergency routes, determine priority for road clearance, and support rescue efforts based on sensing information and integrated analysis results. Such switching is controlled by software based on the operational policy of the entire system, and it is not necessary to provide a dedicated "operation switching unit." For example, in normal mode, the analysis unit can apply processing parameters that focus on cavity risk assessment and abnormality detection, and in disaster mode, the determination unit can perform processing that focuses on extracting roadblocks with high disaster priority and selecting corresponding routes.

[0067] Furthermore, the normal operation mode and the disaster operation mode may include a configuration for switching the risk determination criteria (threshold setting) in the integrated analysis and the prioritization logic for the on-site investigation target points. For example, in normal times, to prioritize wide-area and comprehensive sign detection, the threshold for anomaly detection is set relatively lenient, making it easier to detect potential risks, while in the event of a disaster, the threshold for determining anomaly scores is set stricter, enabling operations to prioritize the extraction and notification of high-risk locations that require rapid response. The road disaster response support system may be configured to dynamically change a risk score calculation, a judgment threshold for anomaly detection, or a prioritization logic for on-site investigation target points depending on whether the system is in a normal operation mode or a disaster operation mode, as shown in the following examples, but is not limited to these.

[0068] The road disaster response support system 600 of the present invention may be configured to continuously acquire and analyze sensing information on disasters, damage, and recovery status, etc., and dynamically reevaluate and reconfigure the analysis results and response plans based on the latest information as needed. This enables flexible responses that respond quickly to changes in the disaster situation.

[0069] To accommodate a variety of users, including foreign tourists, the road disaster response support system 600 may execute notification control processing in the analysis unit 620, the determination unit 630, or the information provision unit according to the user's attribute information and language used. For example, the system may be configured to utilize language setting information and GPS information of the terminal device to automatically notify the user of disaster information and travel route information in the user's language if a dangerous area is present within the foreign tourist's range of movement. Disaster response information may also be provided through a traveler application in cooperation with local governments and tourist facilities. Furthermore, the road disaster response support system 600 may be configured to support foreign languages, and may be configured to output and notify analysis results or road clearance implementation plans translated into multiple languages ​​such as English, Chinese, and Korean via information terminals for foreigners, smartphones, web portals, etc. This makes it possible to deliver accurate and immediate disaster response information to users whose native language is a foreign language. In this case, translation processing and multilingual support can employ an automatic translation configuration that utilizes a large-scale language model (LLM). For example, a pre-trained multilingual translation model can be used to convert specialized disaster terminology and road management terminology into accurate and natural expressions. Furthermore, the system can be configured to dynamically switch the optimal translation model or output format based on the user's device language settings, location information, past usage history, etc., enabling real-time, individually optimized multilingual support. This minimizes delays and misunderstandings in information transmission due to language barriers, enabling safe and effective disaster response support for all users, including foreigners.

[0070] So far, we have provided a basic explanation of road disaster response, mainly aimed at road managers, but from this paragraph onwards, we will explain specific examples in which the road disaster response support system 600 can be equipped with an embodiment of the invention by a road service provider. The road disaster response support system 600 is mainly used by road service businesses to respond to requests for rescue. In addition to the rescue request reception information managed by the company itself, the business operator will acquire rescue activity information obtained through rescue vehicles or drive recorders installed in the vehicles, small unmanned aerial vehicles (drones), portable information devices, etc., as well as at least two types of report information from members, and collect these in an integrated manner. The collected information is analyzed using artificial intelligence to evaluate the possibility of road disasters, the extent of damage, the impact on traffic, and the priority of rescue operations, and is used to determine whether rescue vehicles can pass and to help formulate appropriate rescue operation plans. In addition, the derived disaster scores, optimal routes, and support information are visualized on a dashboard installed in the operator's control room, and are also sent to the mobile devices of field personnel or member terminals as needed, enabling rapid and accurate rescue operations. Furthermore, after the rescue operation, the collected performance data is stored as re-learning data for the artificial intelligence model, allowing for continuous improvement in analytical accuracy and the ability to optimize rescue operation plans. In this way, the road disaster response support system 600 according to the present invention enables road service providers to consistently collect information, assess the situation, formulate and implement a support plan, and reflect the results when responding to a rescue request.

[0071] In this embodiment, the rescue request reception information includes, for example, a rescue request with location information sent by a member via a dedicated smartphone app or call center, and includes the requester's current location, vehicle information, and the details of the request (dead battery, flat tire, accident, etc.). This data is sent to the management server in real time and is used to determine whether a rescue vehicle can be dispatched and to determine priority.

[0072] As an example of how rescue operation information is acquired, a drone can fly ahead to the area before the arrival of rescue vehicles, capture images of road closures from the sky, and then use AI (artificial intelligence) to analyze the images and detect obstacles such as flooding and fallen trees. The acquired information is used to determine in advance whether rescue vehicles can pass through.

[0073] The information acquisition process in the road disaster response support system 600 targets at least two types of information among rescue request reception information, rescue activity acquisition information, and member notification information. For example, by combining the location information and request content obtained when a rescue request is received from a member with video data and still image data obtained from a drive recorder or a small unmanned aerial vehicle (drone) mounted on the rescue vehicle, the situation at the rescue site can be grasped quickly and in detail. Furthermore, this information can be collected during rescue operations or before arrival, allowing for pattern analysis of rescue requests, such as concentration, geographical distribution, and time of occurrence, and can be used to score and prioritize road disasters. In addition, the rescue request reception information can include attribute information such as the type of vehicle to be rescued, the rescue content, and the condition of the person requesting rescue, which allows for more detailed and accurate decisions when formulating a rescue operation plan. This information acquisition function enables more accurate rescue plans to be drawn up between the time a rescue request is made and the time rescue arrives at the scene, thereby speeding up initial responses.

[0074] The analysis process can be a two-stage process in which each piece of acquired information is analyzed individually by type, and then an integrated analysis process is used to evaluate the degree of geographical and temporal concentration. For example, the individual analysis can tally up the frequency of rescue requests by time period, detect the presence or absence of road disasters from the rescue operation information acquired, and then integrate these to calculate a risk score for a specific area.

[0075] Next, a process for generating support information necessary for rescue operations will be described. In this embodiment, support information for supporting the deployment plan of rescue vehicles and personnel is generated based on the density score and analysis results. This support information includes elements such as the type and quantity of equipment and materials possessed by each base or branch, the skills and deployment status of available personnel, and the expected time period and possible range of rescue operations. By taking these factors into consideration, support information is generated to determine the optimal combination of vehicles and personnel for each rescue request and rescue operation. The generated support information reflects the extent of the disaster's impact and the concentration of rescue requests, and can also be used for planning support coordination between multiple bases and wide-area personnel movement plans.

[0076] The specific processing flow for generating support information can be composed of the following steps: (1) calculating the density score of rescue requests, (2) obtaining information on available personnel and equipment at each base, (3) sequentially performing calculations that combine multiple elements to determine the order of response, and (4) selecting rescue vehicles and proposing the optimal rescue route.

[0077] Furthermore, this embodiment includes a process for selecting a response measure suitable for rescue operations from among a plurality of response measures based on the support information and rescue request content, and generating response proposal information regarding the execution of each response measure. The response measures include selection of the type of rescue vehicle, selection of the arrival route at the site, the method of transporting necessary equipment and materials, and decision on activation of a wide-area support system. The response proposal information is generated taking into account the priority score, the operational status of each branch, geographical conditions, traffic control information, etc., and is displayed on the dashboard of the rescue command center, and is also configured to be notified to the mobile devices of on-site personnel and related parties. This will enable the overall disaster response to be speeded up and made more efficient.

[0078] As a specific example of the response proposal information generation process, a rule can be set that limits the type of rescue vehicle to large tow trucks for requests with a high priority score, and conversely, prioritizes the allocation of small service cars for minor rescue requests. It can also include a process for recalculating recommended routes based on traffic regulation information and reflecting the latest congestion information.

[0079] The flow for selecting response measures can be configured to execute the process in the following order: (1) assess the urgency of the rescue request, (2) calculate the estimated time required to reach the scene, (3) determine whether the candidate route is passable, (4) determine the final configuration of vehicles, personnel, and equipment, and (5) distribute information to on-site personnel and the control room.

[0080] Furthermore, in this embodiment, the AI ​​model used in rescue operations is equipped with a process for learning or updating the model using rescue request reception information, rescue site information, or member report information. This allows the progress of rescue operations and performance information obtained after rescue operations to be accumulated as learning data, and the accuracy of judgments, priority determinations, optimal route selection, etc. can be improved in subsequent disaster responses. This learning or model update control is automatically executed using the results of rescue operations or information on the traffic history of rescue vehicles as triggers, enabling continuous optimal rescue support.

[0081] In AI model training, for example, by extracting past cases where rescue vehicles had difficulty passing and learning obstacles, road conditions, weather conditions, and time of day as features, it is possible to improve the accuracy of predicting impassability with high precision the next time similar conditions occur.

[0082] As triggers for updating the model, it is effective to configure the system to automatically collect logs of cases where an administrator has flagged a "needs correction" on the dashboard, as well as the results of rescue operations, and logs of unexpected road impassability, and to automatically start the re-learning process when the number of such cases reaches a certain threshold.

[0083] Furthermore, this embodiment is equipped with a process for visualizing and providing various information and analysis results related to rescue operations on a dashboard screen installed in a management base such as a rescue command center. This dashboard can display an integrated disaster score based on the frequency of requests for rescue operations, the results of rescue operation decisions, passable routes, and the deployment status of equipment and personnel at branches and bases, thereby speeding up the command center's understanding of the overall situation of rescue operations and supporting decision-making. If necessary, similar information can also be sent to portable information devices used by field personnel and to members' mobile devices, enabling accurate and timely information sharing between the field and management centers.

[0084] A specific example of a dashboard would be a heat map function that displays each rescue request point on a map with a marker and colors them according to the density of requests, allowing operators to intuitively grasp the rescue request situation over a wide area and immediately decide on the concentrated deployment of resources to areas where rescue requests are concentrated.

[0085] The dashboard update process automatically updates at regular intervals (for example, every 30 seconds) when information is acquired, and by reflecting rescue requests, whether roads are passable, the progress of rescue vehicles, etc. in real time, it is possible to adopt a configuration that allows commands to be issued based on the latest situation at all times.

[0086] Furthermore, in this embodiment, a communication function can be provided for transmitting the estimated arrival time of the rescue vehicle, traffic regulation information, road disaster occurrence status, etc. to a mobile terminal carried by the member based on the acquired and analyzed rescue request acceptance information, rescue operation acquisition information, passable information, etc. This enables the member who is requesting rescue to grasp the progress of the rescue vehicle and the status of the rescue operation in real time, which contributes to reducing anxiety while waiting and smooth handover.

[0087] When sending information to member devices, push notification functions can be used to automatically send notifications when the estimated arrival time of the rescue vehicle or progress status changes, providing real-time peace of mind to the requester.

[0088] The estimated time of arrival of rescue vehicles can be calculated using the latest traffic information and vehicle location information, enabling accurate progress management by dynamically updating the ETA (Estimated Time of Arrival).

[0089] Furthermore, in this embodiment, a function can be provided to transmit the acquired and analyzed rescue request reception information, rescue activity acquisition information, information on impassable areas, the implementation status of rescue support, and information on the estimated arrival time of rescue vehicles to an external system that can be used by road managers, government agencies, or disaster response agencies (fire departments, police, Self-Defense Forces, disaster medical teams, etc.). This enables government agencies and other support agencies to immediately grasp the situation in the disaster area and quickly make decisions on wide-area recovery work and traffic restrictions.

[0090] When sending information to external systems, a standard API interface (such as REST API or WebSocket) can be used to adopt a configuration that allows two-way linkage with disaster information management systems and traffic control systems owned by road managers and government agencies. This allows for mutual updates on rescue operations and traffic control status in real time.

[0091] The transmitted information will not only include the occurrence status, but also detailed information that will assist in decision-making, such as the impact extent score calculated as a result of the analysis and information on recommended candidate routes for lifting restrictions, thereby improving the accuracy of decision-making on the part of the government.

[0092] Furthermore, in this embodiment, it is possible to provide a function for optimizing the wide-area coordinated allocation of personnel and equipment across multiple branches or local governments and the securing of accommodations and support bases, based on information on the equipment and personnel available at each branch or base, the score of the relief activities based on the analysis results, the results of judgments regarding the relief activities, etc. Furthermore, by providing the passage permit information and traffic restriction instructions in the disaster area to the passage permit management system and the entry management system according to these optimization results, it is possible to improve the efficiency of relief activities and the accuracy of disaster area management.

[0093] Regarding wide-area coordinated deployment plans for personnel and equipment, the system can perform multivariate analysis of disaster scores and availability information for each base, list branches and municipalities that can provide support in order of priority, and automatically present recommended plans.

[0094] Furthermore, by managing hotels, inns, and public facilities in disaster-stricken areas as potential accommodation locations and automatically linking them to securing accommodation when planning the dispatch of relief team members, the system can ensure the realistic feasibility of disaster response.

[0095] Furthermore, in this embodiment, when the score related to rescue operations exceeds a predetermined threshold, the system automatically switches its operation mode from normal mode to disaster mode, and the priority of the information to be output and the notification format can be changed according to the progress of the rescue operations and the surrounding circumstances. This enables flexible operation according to the scale and impact of the disaster, and improves the accuracy of initial responses and rescue support.

[0096] In controlling the switching of operation modes, not only a score exceeding a predetermined threshold but also a sudden increase in the number of rescue requests and the results of geographical cluster analysis (a pattern in which requests are concentrated in a small area in a short period of time) can be used as additional trigger conditions. This enables flexible mode switching according to the actual situation on site.

[0097] After switching to disaster mode, the dashboard UI is automatically simplified and the layout is changed to make it easier for control room operators to grasp only priority information, thereby incorporating features to improve operational responsiveness.

[0098] In addition, in this embodiment, the actual disaster situation, the results of rescue operations, the history of rescue vehicle traffic, etc. are collected and accumulated, and the collected history data and the analysis results are used as learning data for the artificial intelligence model, and a process of re-learning or updating the model can be executed. This configuration enables more accurate judgment and support in future disaster responses, making it possible to continuously improve response capabilities.

[0099] When relearning the AI ​​model, learning efficiency can be improved by comparing the rescue vehicle's passability judgment results with the actual passability results (arrival time, driving log, etc.) and focusing on adding incorrect judgment cases as learning data.

[0100] In addition, the timing of re-learning can be configured to be performed in batch processing after multiple disaster responses have been completed, or sequentially after each set amount of new data has been acquired.

[0101] Furthermore, in this embodiment, a security process can be provided to prevent unauthorized access and tampering of communication content and to perform authentication processing for information sent and received between external systems, member mobile terminals, portable information devices used by field personnel, etc. This makes it possible to prevent leaks and unauthorized use of important information during disaster response and ensure the safety of information.

[0102] In security processing, "selective encryption" is performed, which applies encryption processing preferentially only to highly important information such as rescue request reception information and rescue operation acquisition information, thereby achieving both response performance and security strength.

[0103] In addition, by adopting two-way authentication that verifies the certificate of the communication partner (control room or central system) on the terminals of rescue vehicles and on-site personnel, security against man-in-the-middle attacks can be improved.

[0104] Furthermore, in this embodiment, even if some functions are stopped due to communication failure, power failure, equipment failure, etc. during a disaster, the functions can be made redundant by using other network paths, alternative servers, and alternative processing mechanisms, ensuring the continuity of operation of the entire system. With this configuration, rescue operation support functions can be maintained without interruption even in an emergency, making it possible to continue on-site activities and information sharing among related parties.

[0105] In a redundant configuration, the main server normally handles rescue operations, and a failover mechanism can be incorporated that automatically switches to the standby server after detecting a failure.

[0106] In addition, by installing standby servers in multiple geographically separated data centers, it is possible to adopt a configuration that ensures continuous operation of the system even if the disaster itself affects an area that includes the data center.

[0107] Furthermore, in this embodiment, by collecting information such as the occurrence status of an actual disaster, the results of rescue operations, and the passage record of rescue vehicles, and utilizing the accumulated information and the analysis results as learning data for the artificial intelligence model, it is possible to improve the analytical accuracy of the evaluation of the probability of a disaster occurring, the extent of its impact, and the determination of priorities in rescue operations, etc. This makes it possible to provide more advanced decision-making support that reflects past cases even when future disasters occur.

[0108] When analyzing rescue operations, not only are rescue request reception information, rescue operation acquisition information, and member report information analyzed individually, but these multiple pieces of information are integrated and correlation analysis is performed to identify the concentration of rescue requests, the extent of damage, and priority areas for support.

[0109] With correlation analysis, for example, if multiple members make requests in the same area, it is possible to use geographic clustering to assess the risk in that area as higher, or to use natural language processing to analyze the similarity of the reports and infer that they are the same event.

[0110] In addition, in this embodiment, in preparation for a situation in which some functions are stopped due to a communication failure, a power failure, or a device failure in the event of a disaster, each function can be made redundant by using another network path, an alternative server, or an alternative processing mechanism, so that the system as a whole can continue to operate. With this configuration, it is possible to minimize interruptions to service provision even in an emergency.

[0111] It is desirable to include detailed information such as the condition of the affected vehicles included in the request (overturned, flooded, stuck in the snow, etc.), road conditions (depth of snow, depth of flooding, fallen objects, etc.), and local weather (whether it is snowing or raining, temperature, wind speed, etc.).

[0112] By obtaining this detailed information from the time a rescue request is received, it is possible to assess the risk factors and difficulty of work at the disaster site in advance, and this information can be reflected in the preparation and selection of equipment for rescue teams and vehicles.

[0113] In addition, by obtaining the current location and driving history of rescue vehicles in real time and comparing them with passable route information, it is possible to avoid the risk of roads becoming impassable mid-way and assist in switching to an alternative route.

[0114] By integrating and analyzing the driving data of rescue vehicles and information reported by members, it is possible to continuously update the sections that are passable and impassable, and share this information with administrators and other rescue teams, thereby enabling a configuration that supports smooth rescue operations throughout the disaster area.

[0115] Furthermore, video and audio data from rescue sites can be used to quantify the damage situation and assess the level of danger through image recognition and audio analysis using AI models. For example, video footage can be used to detect cracks in the road or fallen trees, and audio can be used to estimate local noise levels and the urgency of those requesting rescue, contributing to highly accurate disaster scoring.

[0116] The results of the AI ​​analysis are automatically reflected on a dashboard used by rescue workers and the command center, and can be configured to update decision-making information in real time as the situation changes.

[0117] In addition, the system can be configured so that the analysis unit processes the various types of collected information individually during rescue operations, or so that multiple pieces of information are integrated and analyzed comprehensively, allowing for a flexible design that can be used depending on the scale of the disaster and the local situation.

[0118] Furthermore, by utilizing the location information contained in the rescue request reception information and rescue operation acquisition information, a configuration can be adopted in which rescue request points, rescue vehicle locations, passable routes, obstacle locations, etc. are visualized on a GIS (geographic information system). This visualization of geographic information makes it possible to intuitively formulate rescue operation priorities and wide-area support plans.

[0119] In addition to the disaster score, the dashboard also displays a list of the operating status of each branch and base, as well as the deployment status of equipment and personnel, providing information to support coordination between multiple branches and personnel shift planning, thereby streamlining command operations during wide-area, complex rescue operations.

[0120] Furthermore, depending on the progress of rescue operations, AI (artificial intelligence) will automatically recalculate the optimal route and notify on-site personnel and the command center of the revised route in real time, enabling the system to be configured to minimize delays and continue rescue operations even in emergencies.

[0121] Furthermore, when determining whether a road is passable based on information on received rescue requests and rescue operation information, it is possible to combine external data such as weather and meteorological information, traffic regulation information, and road damage information, and use AI (artificial intelligence) to make a multifaceted determination. This makes it possible to go beyond the conventional simple route determination and formulate an advanced rescue plan that can respond to complex road conditions when a disaster occurs.

[0122] Furthermore, the system can be equipped with an algorithm that dynamically reallocates rescue vehicles and personnel and updates routes, instantly reflecting new rescue requests that arise during rescue operations and changes in the status of existing requests (cancellations, location changes, etc.), thereby making effective use of rescue resources and maximizing the efficiency of rescue operations.

[0123] In addition, by storing time-series data from the receipt of a rescue request to its completion, and providing a data management function that systematically organizes and manages the data as learning data for future AI models, it will be possible to improve the performance of the AI ​​model over the long term.

[0124] Furthermore, when calculating the priority of a rescue request, the system is equipped with a process that can dynamically change the priority by taking into account the urgency of the requester in the rescue request reception information (for example, the degree of danger to life and body), the traffic importance of the request point on the road network (whether it is a main road or a residential road, etc.), as well as the number of simultaneous requests and the operating status of branches.

[0125] Furthermore, by visualizing multiple assessment information such as disaster scores, traffic impact levels, and rescue operation schedules in a multidimensional manner and providing a dashboard screen that allows comprehensive decision-making in the command center, it is possible to grasp the situation comprehensively between the field and management bases.

[0126] In addition, by collecting on-site video, audio, and environmental data obtained during rescue operations in real time, and updating the disaster situation as it occurs, and using this information as feedback to the AI ​​model, the accuracy and responsiveness of rescue operations can be further improved.

[0127] Furthermore, the various types of information acquired can be analyzed individually for each rescue request, or multiple rescue requests that are geographically or temporally close can be analyzed together, providing a structure that allows for flexible scoring and priority evaluation according to the different disaster response needs for each request and region.

[0128] In addition, information based on the analysis results, such as whether rescue operations are possible and recommended routes, can be linked to the devices used by on-site personnel to provide navigation support, allowing personnel to select appropriate entry routes at the disaster site and carry out rescue operations safely and quickly.

[0129] Furthermore, by notifying members who request rescue of the progress of the rescue vehicle, the estimated time of arrival, recommended waiting locations, etc., the system helps the requester optimize their own actions, thereby facilitating rescue operations and increasing the requester's sense of security.

[0130] Furthermore, when acquiring rescue request reception information, rescue operation acquisition information, and member notification information, attribute data contained in each piece of information (time of request occurrence, location coordinates, road section identifier, road type, traffic volume index, etc.) can be assigned and managed as metadata, and these attributes can be referenced during subsequent integrated analysis and rescue plan formulation, thereby improving the searchability, traceability, and analytical accuracy of the information.

[0131] Furthermore, statistical analysis using various attribute information can be used to understand trends in rescue requests from multiple angles, such as by time series, region, and road type, and this information can be used for advance training and disaster prevention planning during normal times, and to optimize rescue resource deployment strategies when a disaster occurs.

[0132] Additionally, this embodiment can perform image analysis on the cloud for still and video data acquired from rescue operation sites, and can automatically classify disaster elements such as snow accumulation, flooding, fallen trees, road collapses, etc. The results of this analysis can be used to quantitatively assess the disaster impact, prioritize rescue routes, and support the selection of equipment and materials, contributing to quick and accurate response decisions.

[0133] In addition, this automatic classification process can be combined with time and location information to generate a heat map, which visualizes areas where disasters are concentrated, providing intuitive support for understanding the extent of the damage.

[0134] Furthermore, in this embodiment, it is possible to analyze the voice data included in the rescue operation acquisition information, and for example, it is possible to provide a voice analysis process that estimates the urgency and danger level from the voice of the person in need of rescue or the person making the call. This makes it possible to grasp the situation on site from multiple angles and assist in determining the priority of rescue operations.

[0135] Furthermore, these audio analysis results are integrated with video analysis results, location information, and report content, and are used as indicators for comprehensive rescue scoring and risk ranking, allowing the rescue command center to quantitatively grasp the level of urgency at the scene and quickly decide on a response policy.

[0136] Furthermore, in this embodiment, the video data and still image data acquired as rescue operation information are subjected to analysis processing using image recognition technology, making it possible to detect specific disaster elements, such as obstacles on the road, flooding, sinkholes, collapsed bridges, etc. The results of this analysis are used to determine whether rescue vehicles can pass through and for risk assessment when formulating rescue operation plans.

[0137] In addition, the detection results from the image recognition can be integrated and analyzed with other acquired information (rescue request reception information, member notification information, traffic regulation information, etc.), and the location and range of obstacles can be visualized on a dashboard by plotting them on a map. This allows rescue command center and on-site personnel to intuitively grasp the spatial situation of the disaster, enabling them to quickly select appropriate evacuation and rescue routes.

[0138] Furthermore, in this embodiment, when relearning the artificial intelligence model based on the results of rescue operations, not only rescue request data under normal circumstances but also specific rescue request reception information and rescue operation results during large-scale disasters can be separately managed, and models for normal times and disasters can be stored separately. This makes it possible to switch to an appropriate model depending on the different rescue patterns between normal times and disasters, optimizing judgment accuracy. Relearning can be performed using batch processing performed all at once after the disaster response is completed, or using an online learning method based on rescue results transmitted sequentially from the site, helping to maintain the accuracy required for rescue operations.

[0139] Furthermore, in this embodiment, a dashboard screen installed in a rescue command center or the like is configured to superimpose acquired rescue request reception information, rescue activity acquisition information, passable road information, etc. on a map, and to visualize the current location, traveling direction, and expected arrival time of the rescue vehicle in real time. The map screen can be integrated with a color-coded display indicating the priority of the rescue request, a pop-up function that displays detailed information about the rescue request, a list view that shows the operating status of multiple bases, etc., allowing the manager to intuitively grasp the situation and quickly give appropriate instructions.

[0140] Furthermore, in this embodiment, when the AI ​​model learns the results of rescue operations, the traffic history information of rescue vehicles, and the analysis results, the AI ​​model is configured to link and store the details of the rescue request and on-site situation data, as well as historical information on the determination of passability, information on the route used in the rescue operation, and the time required to complete the rescue. By using this information group as training data to retrain the AI ​​model, it is possible to achieve highly accurate rescue necessity determination, priority evaluation, and route selection in future disasters. Furthermore, the learned model is gradually reflected in the operational environment, and continuous performance improvement is achieved through model updates.

[0141] Furthermore, in this embodiment, the system may be configured to include an AI model management server to manage the learning and updating of the AI ​​model. The AI ​​model management server performs tasks such as registering learning datasets, managing versions, monitoring learning progress, and verifying learning results, and plays a role in centrally managing the entire learning process. This prevents tampering with or incorrect registration of learning data, ensures the reliability of the learning process, and makes it possible to maintain a certain level of quality for the AI ​​models used in rescue operations.

[0142] Furthermore, this embodiment may include a model performance verification process after relearning or updating the AI ​​model. In this performance verification process, a simulated rescue scenario is executed using the updated AI model, and the validity of the judgment results and rescue plan is evaluated. The evaluation is performed automatically based on past actual disaster data and standardized test cases, and if the evaluation results do not meet predetermined standards, the model can be prevented from being applied to on-site operations. This makes it possible to objectively confirm the quality of the updated AI model and improve the reliability of the entire rescue support system.

[0143] This embodiment may also include a history management process for managing the operation history of the AI ​​model. This history management process chronologically stores information such as the version of the AI ​​model's learning data, the date and time of re-learning or updates, the update content, and the results of operational verification after the update, allowing the administrator to check it as needed. History management information is important in that it centrally grasps the operation status of the AI ​​model and makes it possible to explain the model's behavior during disaster response and post-event verification. This enables strict change management of the AI ​​model and ensures the transparency and reliability of disaster relief operations.

[0144] Furthermore, this embodiment may include a process for automatically switching and failing over AI models. This process automatically switches to a predefined alternative AI model if the AI ​​model detects an abnormality during rescue operations or if the model's response delay exceeds an acceptable range. When switching, the current rescue request reception information and analysis results are retained, allowing processing to continue without affecting rescue operations. This reduces the risk of system outages caused by AI models and increases the stability and reliability of disaster response support.

[0145] Furthermore, this embodiment may include a process for automatically evaluating the analytical accuracy and rescue plan formulation accuracy of the AI ​​model using activity performance data acquired when rescue operations are completed. This process compares performance data, such as the content of the rescue request, the arrival time of the rescue vehicle, the actual rescue completion time, and local environmental factors, with the inference results of the AI ​​model to quantitatively calculate errors and deviations. The evaluation results can be used to determine whether or not the model needs to be updated and to assign priorities, contributing to the ongoing maintenance and improvement of model accuracy.

[0146] Furthermore, in this embodiment, in order to monitor the progress of rescue operations in real time, a process may be provided in which the current location of rescue vehicles, the time spent at the site, the response status, the status of communication with the rescue requester, etc. are aggregated and reflected on the management screen. This process allows the command center or manager to grasp the progress of multiple rescue requests from a bird's-eye view, and enables them to immediately request additional support or give instructions in the event of a delay or trouble. This supports the smooth progress of the entire rescue operation.

[0147] Furthermore, this embodiment may include a process for automatically reevaluating and changing the priority of rescue requests in response to additional information collected during rescue operations, new rescue requests, changes in road conditions, worsening weather, etc. This priority change process enables the command center to update the support plan in response to changes in the situation, thereby improving the efficiency of the entire rescue operation and ensuring the safety of those requesting rescue.

[0148] This embodiment may also include a process for predicting the time required for a rescue vehicle to arrive at the scene. This prediction is performed taking into consideration the current location information of the rescue vehicle, road traffic conditions, traffic regulation information, weather conditions, etc., and the estimated arrival time of the rescue vehicle can be calculated with high accuracy. The calculated estimated arrival time can be notified to the member terminal, the mobile device of the on-site crew, or relevant organizations, and can be used to smoothly carry out rescue operations and coordinate standby at the scene.

[0149] Furthermore, this embodiment may include a process for automatically recording a series of processes in rescue operations. This process automatically records the time of receipt of the rescue request, the departure time of the rescue vehicle, the time of arrival at the site, the start and end time of the rescue operation, the acquired video and image data, the behavioral history of the rescue vehicle and on-site personnel, etc. in chronological order, and can automatically generate a rescue operation report. The generated report can be used by the operator's control room or management department to manage the progress and improve the quality of the rescue operation, and can also be used as documentation to submit to related organizations as necessary.

[0150] In addition, in this embodiment, if an abnormality occurs in the progress of the rescue operation or the local situation based on various data acquired during the rescue operation, the system may automatically detect the abnormality and urgently reevaluate the analysis results and priorities. Examples of abnormalities include unexpected road blockages, significant delays in the arrival of rescue vehicles, and sudden deterioration of weather. When these are detected, support information can be dynamically recalculated and notified to the command center and on-site personnel to prompt appropriate response.

[0151] Furthermore, in this embodiment, in order to strengthen support in rescue operations based on the local situation, a function may be provided to remotely control cameras mounted on rescue vehicles and small unmanned aerial vehicles (drones) from a control center such as a command center. This function allows an operator at the control center to grasp the detailed situation in real time before and after arriving at the site. In addition, the results of video and image acquisition by remote control can be used to revise rescue plans and give accurate instructions to on-site personnel.

[0152] In addition, this embodiment may be equipped with a communication function that enables real-time communication via voice calls or chat messages between on-site rescue workers and the management center or members during rescue operations. This allows detailed information and changes in the situation at the disaster site to be quickly shared, allowing rescue operations to proceed while receiving appropriate support for making decisions. Voice data and text data are recorded as rescue operation history and can be used for future verification or as learning data for AI models.

[0153] Furthermore, in this embodiment, a function for managing authority for access to rescue operation acquired information and various analysis results may be provided. This makes it possible to set access authority according to the role of the user, such as the rescue command center manager, on-site personnel, or cooperating organizations, and provide only the minimum amount of information necessary. This reduces the risk of information leaks and operational errors, and allows each user to safely and smoothly carry out rescue operations in accordance with their own role.

[0154] Furthermore, this embodiment may have a function for automatically controlling the notification frequency according to the situation when notifying members and on-site personnel of various disaster response-related information. For example, if rescue operations are stalled, progress status updates may be sent periodically, and if the situation suddenly changes, notifications may be sent immediately. This allows users to receive the information they need at the appropriate time, preventing confusion and anxiety caused by information overload.

[0155] In addition, in this embodiment, in case of a communication failure or temporary connection failure when notifying a member terminal or a field worker terminal, a function can be provided to automatically retry the notification after a certain period of time. This function minimizes the omission of important information even in an emergency, making it possible to reliably deliver necessary information to users. Note that the number of retries and the interval between retries may be dynamically changed depending on the disaster situation and network conditions.

[0156] Furthermore, in this embodiment, the location information of the member terminal or the on-site crew terminal can be used to optimize the timing of notifications based on the current location of each terminal. For example, it is possible to provide timely information according to the user's location, such as sending estimated arrival information when a rescue vehicle is about to arrive, or notifying the user of passable route information before approaching a traffic jam or restricted area. This configuration can facilitate user behavior during rescue operations and waiting, and help users understand the situation.

[0157] Furthermore, in this embodiment, when disaster occurrence prediction and road condition evaluation are performed using an AI model, various meteorological data such as precipitation, snowfall, air temperature, road surface temperature, humidity, wind speed, etc. can be combined and analyzed. This makes it possible to detect anomalies based on multiple conditions without relying on a single meteorological element, which can contribute to improving the accuracy of understanding road disaster risks and formulating rescue plans.

[0158] Furthermore, this embodiment includes a process for having the AI ​​model learn case information such as the history of past rescue activities, the occurrence of road disasters, the arrival record of rescue vehicles, and the extent of damage, and then automatically generating a rescue plan by referring to past cases when a similar disaster situation occurs. This makes it possible to utilize empirical knowledge as data and formulate a prompt and appropriate rescue plan based on the results of past responses.

[0159] Furthermore, this embodiment includes a process for continuously updating the road disaster risk assessment model using performance data such as rescue request details, disaster damage status, and rescue response results accumulated through rescue operations. This improves the accuracy of risk assessment that takes into account regional characteristics, weather conditions, and aging deterioration of road infrastructure, and supports more accurate decisions in the formulation of future rescue operations and road management plans.

[0160] Furthermore, in this embodiment, in order to share information in real time with other disaster response organizations such as government agencies, police, fire departments, and the Self-Defense Forces during rescue operations or when formulating a rescue plan, a collaboration function based on standardized data formats and communication protocols can be provided. This configuration allows accurate and immediate exchange of location information, the progress of the disaster, and the deployment status of rescue equipment and personnel between each organization, making it possible to realize wide-area and integrated disaster response.

[0161] Furthermore, in this embodiment, the AI ​​model used to support rescue operations can be provided with a function for managing update and learning histories based on various learning data, including past disaster response results, and for clearly managing model versions. This function makes it possible to track which disaster cases a specific model version was learned and updated on, verify the accuracy improvement process, and enable rollback operations to return to a previous version as necessary.

[0162] Furthermore, this embodiment can be equipped with a function to automatically pause the model update process during rescue operations. This prevents unexpected fluctuations in the AI's judgment results during on-site response, ensuring the stability and consistency of rescue operations. After the rescue operations are completed, the model update process can be automatically resumed.

[0163] Furthermore, in this embodiment, the road disaster response support system 600 can be provided with a process for managing a history of mode switching, such as switching from normal mode to disaster mode and returning from disaster mode to normal mode. This makes it possible to visualize the timeline of rescue activities and the entire disaster response, and to refer to the switching history when analyzing past disaster cases, so that it is possible to reflect this in disaster response plans for the next and subsequent disasters.

[0164] Furthermore, in this embodiment, a process can be provided for periodically monitoring the operation status of various modules (information acquisition, analysis, support information generation, communication, etc.) in the road disaster response support system 600 and saving the results as an operation status log. This makes it possible to check the operation status of each module during disaster response or when reviewing after a disaster, identify the location of a failure or the cause of a processing delay, and use the information for operational improvement and system maintenance.

[0165] In addition, this embodiment can be configured to manage the collected rescue request reception information and rescue activity acquisition information in a time-series manner and store them as a disaster time-series database. This configuration makes it possible to reproduce the entire process from the occurrence of a disaster to the completion of rescue efforts along the timeline, and to use this information as reference information for verifying past cases and formulating future rescue plans.

[0166] In this embodiment, a function may be provided to display passable route information and the current location information of rescue vehicles in map format on the screen of a member terminal or a field crew terminal. This display function allows members and crew members to intuitively understand the route situation by indicating road blockages and traffic restrictions with icons or color coding, thereby helping members and crew members make decisions to respond quickly on site. In addition, by displaying the calculated estimated time of arrival on a map, the waiting requester can visually understand the progress of the rescue vehicle, improving their sense of security and promoting a smooth delivery.

[0167] Furthermore, this embodiment can be configured to acquire information on the types and quantities of materials and equipment needed for rescue operations in cooperation with the inventory management systems of each branch or base, and reflect this information in rescue plans. This allows the location, quantity, and availability of necessary materials and equipment to be grasped in real time, and a plan to transport materials and equipment from the most appropriate branch or base can be automatically formulated. The transport plan is optimized according to traffic control information and road disaster scores, making it possible to improve the speed and efficiency of rescue operations.

[0168] Furthermore, this embodiment can be configured to track the traveling status of the rescue vehicle as it heads to the scene in real time, and display the current location and progress of the rescue vehicle on a dashboard in the control room. This allows the control room to grasp the estimated arrival time of the rescue vehicle and issue instructions to change the route in response to traffic congestion, road closures, etc. that occur along the way, thereby minimizing delays in the entire rescue operation.

[0169] Furthermore, this embodiment can be equipped with a schedule optimization function that takes into account the estimated arrival times of multiple rescue vehicles and support units, avoiding simultaneous entry at the site and adjusting arrivals to occur sequentially. This schedule optimization allows work at the site to proceed efficiently and avoids congestion when transporting rescue equipment and securing work space.

[0170] Furthermore, this embodiment can be configured to monitor external factors such as local traffic conditions and weather changes in real time after the dispatch of a rescue vehicle, predict the impact of these factors on rescue operations, and automatically suggest, as necessary, changing the route of the rescue vehicle, recalculating the estimated time of arrival, requesting alternative support, etc. This configuration makes it possible to flexibly respond to changes in the on-site environment.

[0171] Furthermore, in this embodiment, it is possible to provide a function that allows information related to rescue operations acquired by each base and command center to be managed by dividing it into regions and bases. This makes it possible to grasp the situation in each region individually and optimize the support system on a regional basis, even when rescue operations are carried out simultaneously in multiple regions, such as in the event of a large-scale disaster, thereby improving the efficiency of overall operations.

[0172] Furthermore, this embodiment can be provided with a function for managing various information used in rescue operations in chronological order, and for referencing the entire history from the rescue request to the completion of the rescue in timeline format. This timeline includes the time of receiving the rescue request, the time of arrival at the site, the time of work start and completion, and the rescue results, allowing the command center and managers to easily grasp the progress of the rescue operations and support rapid decision-making.

[0173] Furthermore, in this embodiment, when multiple rescue requests occur simultaneously, a function can be provided that manages the response status for each rescue request independently and formulates parallel rescue operation plans according to priority. This function makes it possible to respond to multiple requests in the optimal order even in situations where requests are concentrated in a short period of time, such as immediately after a disaster occurs, thereby improving the efficiency of on-site responses and preventing confusion.

[0174] Furthermore, this embodiment can be provided with a function that generates progress management information linked to each rescue request and can share it with the rescue command center, on-site personnel, and member terminals. The progress management information includes the departure, arrival, and completion times of rescue vehicles, the work content at the site, and the completion status of each process, allowing all parties involved to accurately grasp the progress of rescue operations and improve the accuracy and speed of collaboration.

[0175] Furthermore, this embodiment can be provided with a function for managing history information of rescue requests. This history information includes the request content, the time required for response, the route and activity of the rescue vehicle, various judgment results, etc. By storing and referencing past cases, it can be used to speed up and optimize initial responses and the allocation of equipment and personnel in similar situations.

[0176] This embodiment also has a function for aggregating information on received rescue requests from members when a disaster occurs and generating a heat map based on geographical distribution. This heat map is used to visually grasp the scale of the disaster and the degree of local concentration of damage, and is useful for command centers and managers to quickly determine priority response areas and efficiently deploy rescue vehicles and personnel.

[0177] Furthermore, this embodiment can be equipped with a function that uses natural language processing technology to analyze text data (such as the reason for rescue and an explanation of the situation) included in the rescue request reception information from members and scores the urgency level based on the content and expressions of the utterance. This makes it possible to quantify the urgency of the requester, which is difficult to grasp based on simple location and number information alone, and to more appropriately determine the priority of rescue operations.

[0178] Furthermore, this embodiment can be configured to automatically extract information about the chaotic situation at the scene, the degree of danger in the surrounding environment, and so on from audio data and video data acquired during rescue operations using voice recognition and video analysis, and use this information as support information for rescue operations. This information is displayed in real time on a dashboard and is also used to optimize rescue plans.

[0179] Furthermore, this embodiment is configured to enable on-site personnel to send text and audio feedback regarding the rescue situation via portable information devices carried by the personnel during the rescue operation. This feedback is immediately reflected in the support plan, rescue operation priorities, route information, etc., facilitating quicker decision-making in the command room and sharing of information with other on-site personnel.

[0180] This embodiment also includes a status recording function for situations during and after rescue operations, allowing for the automatic recording of time-stamped information, such as the location history of rescue vehicles, time spent at the site, video and audio logs during operations, and road infrastructure status data acquired during operations. This recorded information can be used for post-disaster recovery activity plans, government reports, and training feedback, and can also be used as training data for retraining AI models. This allows for the use of detailed logs of field activities to improve the quality and efficiency of rescue operations.

[0181] Furthermore, this embodiment is equipped with a function for switching communication paths related to rescue activities, and although existing mobile lines are normally used, in the event of a base station failure or communication congestion during a disaster, it can automatically switch to alternative paths such as satellite communication, mesh network, or Wi-Fi Direct communication. This makes it possible to continue sending and receiving important information between rescue vehicles, the command center, on-site personnel, and members even during an emergency, reducing delays in activities and information interruptions caused by the unstable communication environment during a disaster.

[0182] Furthermore, this embodiment has a function of using AI (artificial intelligence) to perform real-time analysis of on-site video and still image data acquired during the progress of rescue operations, and automatically detecting road obstacles, flooded areas, signs of landslides, etc. The detection results are immediately provided to the command center and on-site personnel as support information necessary for rescue operations, and are used to identify dangerous areas, decide on route changes, arrange for additional equipment, etc.

[0183] Furthermore, this embodiment has a function of utilizing driving data from the rescue vehicle while it is in operation to automatically analyze changes in road conditions and the driving environment from speed changes, sudden stops, vibration data, etc. The results of this analysis can detect risk signs such as frozen roads and potholes early on, and provide warnings to the rescue command center and following rescue vehicles, thereby preventing secondary disasters during rescue operations.

[0184] This embodiment also has a function that converts voice reports from on-site personnel into text in real time using voice data acquired during rescue operations. The converted text information is automatically displayed on the dashboard, allowing the command center to immediately grasp the situation at the site, and the voice content can also be saved in a database and used to improve disaster response in the future.

[0185] Furthermore, this embodiment is equipped with a function that performs image analysis using AI (artificial intelligence) on video data acquired during rescue operations, automatically identifying the presence or absence of road closures and the type of obstacles at the scene. The identification results are visualized in an easy-to-understand manner on a dashboard, helping to immediately consider countermeasures according to the type and scale of the obstacle. In addition, the image analysis results are saved as history and can be used for future disaster response evaluations and as learning data.

[0186] Furthermore, in this embodiment, in order to efficiently process multiple simultaneous rescue requests during a large-scale disaster when rescue requests are concentrated, the system is equipped with a function for mapping rescue request reception information in real time and analyzing and visualizing the geographic concentration of request locations using AI (artificial intelligence). This enables the rescue command center to grasp the distribution of simultaneous rescue requests and quickly determine wide-area priorities and efficiently allocate resources.

[0187] Furthermore, this embodiment includes a process for collecting and recording information such as the operating status, movement history, and rescue completion time of rescue vehicles, and automatically generating a work history for each vehicle. This allows the operating rate and response performance of each rescue vehicle to be quantitatively grasped, which can be used for business operator business management and optimization of future vehicle deployment plans.

[0188] This embodiment also includes a process for estimating secondary disasters and additional risks that may occur during rescue operations based on the collected rescue operation information and on-site environmental data. This process makes it possible to identify areas with increased risks, such as rockfalls and flooding, and generate and provide warning information to on-site personnel and the command center to help ensure safety during rescue operations.

[0189] Furthermore, in this embodiment, when evaluating passable routes in rescue operations, a process is provided that takes into account physical characteristics of the rescue vehicle, such as size, turning radius, vehicle height, and load weight. This makes it possible to determine the passability of each rescue vehicle in detail, rather than simply relying on static information such as road width and gradient, and to select a route optimized for each vehicle.

[0190] In addition, in this embodiment, when determining the priority of rescue operations, a weighting process can be performed according to the urgency level in the disaster area. For example, a high weight can be assigned in scoring to rescue requests in areas where saving lives is a priority or around medical institutions, while a low weight can be assigned to requests in areas where the impact on traffic is limited, allowing for flexible prioritization according to the situation.

[0191] In this embodiment, when collected and analyzed information on disaster situations, relief activities, road infrastructure status, and other information is shared between support centers, other local governments, and related contractors during a disaster, access control can be applied according to the authority and role of the information recipient. For example, by providing comprehensive information on a wide area to branch managers, information limited to their assigned area to field personnel, and only the minimum necessary information to external contractors, it is possible to support smooth collaboration while preventing information leaks and misuse. This access control is achieved by means of ID / password authentication, digital certificates, terminal authentication, and other methods, ensuring both information security and on-site operability.

[0192] This embodiment can be equipped with a notification control process that dynamically adjusts the content and frequency of information to be notified depending on the disaster situation and the progress of rescue operations. For example, when the damage is limited, progress notifications are sent at a normal frequency, but when the damage expands and the priority of rescue operations changes, the notification frequency can be increased to send more urgent information to relevant parties such as requesters, on-site personnel, and the command center. This function makes it possible to provide necessary information in a timely manner without excess or deficiency, improving the accuracy of situation assessment at the site and management base.

[0193] Furthermore, this embodiment can be equipped with a process for automatically generating a progress report based on information collected during rescue operations and sharing the progress status with the requester, on-site personnel, the command center, government agencies, etc. The progress report can include the location of the rescue vehicle, the start and end times of the work, the details of the activity, the rescue results, the next work schedule, etc., and the report can be provided in a variety of formats, such as a map display, a timeline display, or a text summary. This function reduces the information gap between the parties involved and promotes the sharing of the situation and the rapid decision-making.

[0194] Furthermore, in this embodiment, in preparation for the case where multiple support teams or external contractors are working simultaneously during rescue operations, a multi-agent management function can be provided that manages the progress, location, and operating status of each activity entity in an integrated manner. This makes it possible to avoid overlapping work between entities and lack of support in key areas, enabling command and control that optimizes the entire rescue operation. The multi-agent management function can dynamically update and display the activity status of each entity on a visualization dashboard, helping the command center to give instructions from a bird's-eye view of the entire operation.

[0195] Furthermore, this embodiment can be equipped with a driving monitoring function that collects rescue vehicle driving logs and vehicle status data in real time and, in conjunction with the analysis results, manages the vehicle's health status, remaining fuel, estimated travel time, and other information during rescue operations. This function reduces the risk of vehicle trouble or running out of fuel during rescue operations and makes it possible to quickly arrange for a substitute vehicle or change the route as needed. This information can also be provided to dashboards and on-site crew devices, improving the safety and reliability of rescue operations.

[0196] This embodiment also includes a wide-area reallocation function that reallocates personnel and equipment between branches based on the priority of rescue operations and the operational status of rescue vehicles. This function optimizes cooperation between multiple branches in real time in response to changes in the scale of disasters and sudden increases in the number of rescue requests, and enables the rapid concentration of human and material resources in specific areas. This makes it possible to make the most of limited resources and increase the efficiency of the entire rescue operation.

[0197] Furthermore, this embodiment can be equipped with a process for supporting the selection and preparation of materials and equipment to be loaded onto the rescue vehicle in accordance with the disaster situation and the content of the rescue request. This process comprehensively analyzes the condition of the vehicle to be rescued, the rescue content, the geographical conditions of the planned activity location, the expected work content, etc., and automatically presents the type and quantity of materials and equipment required. This improves work efficiency at the site, reduces the transportation of unnecessary materials and equipment, and enables rapid rescue operations.

[0198] As described above, the road disaster response support system 600 of this embodiment collects and analyzes a variety of information held by road service providers to support rescue activities, thereby making it possible to improve and streamline the entire process from rescue requests to on-site response. Furthermore, by providing continuous model improvement using AI (artificial intelligence), a wide-area collaborative allocation function for personnel and equipment, and a redundancy function in the event of communication failure, it is possible to realize faster and more accurate road disaster response than before.

[0199] In the present invention, the term "mobile terminal device" refers to a general-purpose information terminal carried by a member of the road service provider, including, for example, a mobile phone, a smartphone, a tablet terminal, a laptop computer, a game console, etc. On the other hand, the term "portable information device" refers to a business information device carried by a field crew of the road service provider, including, for example, a business-use tablet terminal used in field work, a rugged portable personal computer, a dedicated terminal for disaster response, etc. The dashboard is a UI screen that displays multiple indicators in an integrated manner on a map or in a list format, allowing users to intuitively grasp support information, judgment results, and so on. Each process or function in this embodiment may be configured as an information acquisition unit, an analysis unit, a decision unit, an improvement unit, etc., as described in the claims.

[0200] <Hardware configuration> FIG. 11 illustrates an example of the hardware configuration of a terminal device TM, a fixed camera CAM, a patrol status providing server 100, an optical fiber investigation status providing server 200, a satellite investigation status providing server 300, a weather status providing server 400, a vehicle driving status providing server 500, and a road disaster response support system 600. This diagram illustrates an example in which the terminal device TM is a mobile phone such as a smartphone. The terminal device TM includes, for example, a CPU 701, a RAM 702, a ROM 703, a secondary storage device 704 such as a flash memory, a touch panel 705, and a wireless communication module 706, all interconnected via an internal bus or a dedicated communication line. Application programs such as a road patrol app are downloaded via a network NW and stored in the secondary storage device 704. The fixed camera CAM includes, for example, a CPU 901, a RAM 902, a ROM 903, a secondary storage device 904 such as a flash memory, a lens / image sensor 905, and a communication device 906, all interconnected via an internal bus or a dedicated communication line. Application programs such as a camera application are downloaded via the network NW and stored in the secondary storage device 904 . Each server includes, for example, a NIC 801, a CPU 802, a RAM 803, a ROM 804, a secondary storage device 805 such as a flash memory or a hard disk drive (HDD), and a drive device 806, all interconnected via an internal bus or a dedicated communication line. A portable storage medium such as an optical disk is attached to the drive device 806. A program stored in the secondary storage device 805 or the portable storage medium attached to the drive device 806 is loaded into the RAM 803 by a DMA controller (not shown) or the like, and executed by the CPU 802, thereby realizing the functional units of each server. Patrol information 640, optical fiber inspection information 650, satellite inspection information 660, weather information 670, vehicle driving information 680, analysis results 690, and judgment results 695 are stored in the secondary storage device 805. Note that each server may be implemented using cloud computing. Furthermore, the road disaster response support system 600 may be configured to be able to communicate with each information providing server in order to acquire and process information relating to the road service situation and the like. Furthermore, the road disaster response support system 600 is configured in a computing environment (cloud or on-premise) that has the memory, processors and storage space required for processing each component such as an improvement unit, a prediction unit, an information provision unit, a road clearance unit, an infrastructure maintenance unit and a robotics unit. Furthermore, the configuration may include computational resources including a GPU (Graphics Processing Unit), a TPU (Tensor Processing Unit), or an AI accelerator to execute AI (Artificial Intelligence) models used in each component. Note that this diagram is an example of the hardware configuration shown in FIG. 11, and other configurations (edge ​​device configuration, IoT node configuration, distributed processing environment, etc.) may be used depending on the embodiment. Furthermore, this embodiment has a configuration that can be applied to the road service provider itself to carry out rescue request response work by integrating rescue request reception information, rescue operation acquisition information, and member notification information held by the road service provider, and therefore can be embodied as an embodiment of the invention by the road service provider itself.

[0201] Although the embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to these embodiments or the illustrated configurations. For example, the technical scope of the present invention also includes configurations not shown but described herein, such as processing functions involved in generating analysis results and judgment results, formulating rescue operation plans based on acquired rescue request reception information, rescue operation acquisition information, and member report information, integrating and analyzing various sensing information (camera footage, drone footage, vehicle driving information, etc.), improving the learning of AI (artificial intelligence) models, and implementing visualization functions using dashboards and feedback functions for rescue operations. Therefore, the present invention can be modified, altered, and substituted in various ways without departing from its spirit and scope. [Explanation of symbols]

[0202] 100: Patrol status server 200: Optical fiber inspection status server 300: Satellite survey status server 400: Weather information server 500: Vehicle driving status server 600: Road Disaster Response Support System 610: Information acquisition department 620: Analysis Department 630: Decision Section 640: Patrol Information 650: Optical fiber survey information 660: Satellite Survey Information 670: Weather information 680: Vehicle driving information 690:Analysis results 695: Judgment result

Claims

1. Information on received rescue requests managed by road service providers regarding responses to rescue requests resulting from natural disasters; and rescue operation acquisition information regarding the road disaster situation or road infrastructure situation acquired when dispatched based on the rescue request by at least one of the road service provider's rescue vehicle, the drive recorder installed in said rescue vehicle, the road service provider's small unmanned aerial vehicle camera, or the road service provider's portable information device; and member report information relating to the road disaster situation or the road infrastructure situation provided by a member of the road service business operator and linked to the member's attribute data; an information acquisition unit that acquires at least two pieces of information; an analysis unit that analyzes the possibility of a road disaster occurring or the possibility of an abnormality in road infrastructure based on the information acquired by the information acquisition unit; Equipped with A road disaster response support system characterized by outputting information regarding support for the road service provider to carry out rescue operations (for example, whether or not rescue operations are necessary, how to make rescue operations more efficient, optimizing response measures, and reducing the burden of decision-making on on-site personnel) based on the analysis results obtained by the analysis unit.

2. The road disaster response support system according to claim 1, The analysis unit, based on the information acquired by the information acquisition unit, Based on at least one of the content, geographic concentration, and time period of occurrence of road disasters included in any of the rescue request reception information, the rescue operation acquisition information, and the member notification information, A road disaster response support system characterized by evaluating the probability of a road disaster occurring or the extent of the impact of a road disaster.

3. The road disaster response support system according to claim 1, The analysis unit, based on the information acquired by the information acquisition unit, Based on the content, geographical information, and number of occurrences of road disasters contained in any of the rescue request reception information, the rescue operation acquisition information, and the member report information, A road disaster response support system characterized by calculating the density of the rescue requests, the rescue activities, or member reports, and deriving a score for the road disaster based on the density.

4. The road disaster response support system according to claim 3, The analysis unit is derived based on the density, Based on the road disaster scores, information on the equipment and materials held at each branch or base, and information on the personnel available to respond, A road disaster response support system characterized by outputting support information for optimizing the deployment of personnel or equipment.

5. The road disaster response support system according to claim 1, The analysis unit, based on the information acquired by the information acquisition unit, Analyzing the content relating to road disasters included in any of the rescue request reception information, the rescue activity acquisition information, and the member report information using artificial intelligence; Determine whether the rescue vehicle of the road service provider is allowed to pass through; A road disaster response support system characterized by outputting at least one of the following based on the results of the judgment: whether or not the rescue operation is necessary, the priority of the rescue operation, or the selection of the rescue vehicle to be used for the rescue operation.

6. The road disaster response support system according to claim 5, The analysis unit, based on the rescue position information, the support base information, and the traffic regulation information, Furthermore, depending on the result of analyzing the rescue operation acquisition information, A road disaster response support system characterized by selecting a passable route for the rescue vehicle.

7. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, A road disaster response support system characterized by having a dashboard that visualizes at least one of the following output by the analysis unit or decision unit: road disaster score, support information, judgment results regarding the rescue activities, and passable route information.

8. The road disaster response support system according to claim 4, The analysis unit, based on the road disaster score and the support information, selecting a response measure suitable for said rescue operation from among a plurality of response measures; A road disaster response support system characterized by outputting response proposal information regarding the execution of the response measures.

9. The road disaster response support system according to claim 1, The improvement unit, based on the information acquired by the information acquisition unit and the analysis result by the analysis unit, Based on at least one of the rescue request reception information, the rescue operation acquisition information, and the member notification information, Performing training or updating of artificial intelligence models; A road disaster response support system characterized by being configured to improve the accuracy of determining road disasters or the accuracy of optimizing the rescue operations.

10. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, At least one of the determination result regarding the rescue operation, the passable route information, and the response proposal information output by the analysis unit or the decision unit, A road disaster response support system characterized by having a communication function for transmitting to the portable information devices carried by the on-site personnel of the road service provider.

11. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, At least one of traffic regulation information, road disaster occurrence status, estimated arrival time of the rescue vehicle, or passable route information output by the analysis unit or the determination unit, A road disaster response support system characterized by having a function for transmitting information to mobile terminal devices carried by members of the road service provider.

12. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, At least one of the information output by the analysis unit or the determination unit regarding the occurrence status of road disasters, impassable locations, the implementation status of the rescue operations, or the estimated arrival time of the rescue vehicle, A road disaster response support system characterized by having a function for transmitting to an external system that can be used by road managers, administrative agencies, or disaster response organizations.

13. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, Based on the road disaster score derived by the analysis unit or the decision unit, the judgment result regarding the rescue operation, and information regarding the equipment and materials held at each branch or base and information regarding the personnel available to respond, Optimize the coordinated deployment of personnel or equipment across multiple branches or multiple municipalities, as well as the securing of accommodation or support bases for personnel, A road disaster response support system characterized by having a control coordination function that provides passage permit information or passage restriction instructions to a passage permit management system or an entry management system for the disaster area.

14. The road disaster response support system according to claim 1, The road disaster response support system, based on the information acquired by the information acquisition unit, When the road disaster score derived by the analysis unit exceeds a predetermined threshold, A road disaster response support system characterized by having a control function that automatically switches the operating mode of the road disaster response support system from normal mode to disaster mode and changes the priority or notification format of the information to be output.

15. The road disaster response support system according to claim 1, The road disaster response support system collects information on the occurrence status of an actual road disaster, the results of the rescue activities, the traffic record of the rescue vehicles, and the analysis results obtained by the analysis unit, The data is stored as learning data for an artificial intelligence model used in the analysis unit, A road disaster response support system characterized by having a function for controlling a model update process for relearning or updating the artificial intelligence model.

16. The road disaster response support system according to claim 1, The road disaster response support system is configured to: A road disaster response support system characterized by having a security cooperation function that prevents unauthorized access, prevents tampering of communication content, and performs authentication processing.

17. The road disaster response support system according to claim 1, The road disaster response support system is designed to respond to the suspension of some functions due to communication failure, power failure, or equipment failure during a disaster by: A road disaster response support system characterized by having a configuration that ensures the continuity of operation of the entire system by providing redundancy in the event of a stoppage of the function in question using other network routes (including satellite communications), alternative servers, or alternative processing mechanisms.

18. A program for causing a computer to function as the road disaster response support system according to claim 1, The program causes the computer to: (i) at least one of the functions set forth in claims 2, 3, 5, 7, and 9 to 17; or (ii) at least one of the following functions (1) to (3): or both of the following: (1) A function to output support information to optimize the deployment of personnel or equipment based on road disaster scores, information on the equipment held at each branch or base, and information on the personnel available to respond; (2) A function to select a passable route for rescue vehicles based on rescue location information, support base information, and traffic regulation information, and also based on the analysis results of rescue operation information; (3) A function to select a response measure suitable for rescue operations from among multiple response measures based on the road disaster score and support information, and to output response proposal information regarding the implementation of the response measure.

19. A road management support method using a computer, comprising: The computer communicates with the network via Information on received rescue requests managed by road service providers regarding responses to rescue requests resulting from natural disasters; and rescue operation acquisition information regarding the road disaster situation or road infrastructure situation acquired when dispatched based on the rescue request by at least one of the road service provider's rescue vehicle, the drive recorder installed in said rescue vehicle, the road service provider's small unmanned aerial vehicle camera, or the road service provider's portable information device; and member report information relating to the road disaster situation or the road infrastructure situation provided by a member of the road service business operator and linked to the member's attribute data; We obtain at least two pieces of information from the following: Analyzing the possibility of a road disaster or an abnormality in road infrastructure based on the acquired information; A road management support method characterized by outputting information regarding support for the road service provider to carry out rescue operations (e.g., whether or not rescue operations are necessary, how to make rescue operations more efficient, optimizing response measures, and reducing the burden of decision-making on on-site personnel) based on the analysis results.

20. 20. The road management support method according to claim 19, The computer executes the following via the network based on the acquired information: Based on at least one of the content, geographic concentration, and time period of occurrence of road disasters included in any of the rescue request reception information, the rescue operation acquisition information, and the member notification information, A road management support method characterized by evaluating the probability of a road disaster occurring or the extent of the impact of a road disaster.

21. 20. The road management support method according to claim 19, The computer executes the following via the network based on the acquired information: Based on the content, geographical information, and number of occurrences of road disasters contained in any of the rescue request reception information, the rescue operation acquisition information, and the member report information, A road management support method characterized by calculating a density relating to the rescue requests, the rescue activities, or member reports, and deriving a road disaster score based on the density.

22. 22. The road management support method according to claim 21, The computer receives, via a network, the information derived based on the density. Based on the road disaster scores, information on the equipment and materials held at each branch or base, and information on the personnel available to respond, A road management support method characterized by outputting support information for optimizing the allocation of said personnel or said equipment and materials.

23. 20. The road management support method according to claim 19, The computer executes the following via the network based on the acquired information: Analyzing the content relating to road disasters included in any of the rescue request reception information, the rescue activity acquisition information, and the member report information using artificial intelligence; Determine whether the rescue vehicle of the road service provider is allowed to pass through; A road management support method characterized by outputting at least one of the following based on the results of the judgment: whether or not the rescue operation needs to be carried out, the priority of the rescue operation, or the selection of the rescue vehicle to be used in the rescue operation.

24. 24. The road management support method according to claim 23, The computer, based on the rescue position information, the support base information, and the traffic regulation information, Furthermore, depending on the result of analyzing the rescue operation acquisition information, A road management support method characterized by selecting a route that is passable for the rescue vehicle.

25. 20. The road management support method according to claim 19, The computer outputs the information based on the acquired information via a network. A road management support method characterized by visualizing and displaying as a dashboard at least one of road disaster scores, support information, judgment results regarding the rescue activities, and passable route information.

26. 23. The road management support method according to claim 22, The computer, via a network, performs the following operation based on the road disaster score and the support information: selecting a response measure suitable for said rescue operation from among a plurality of response measures; A road management support method characterized by outputting countermeasure proposal information regarding the execution of the countermeasure measures.

27. 20. The road management support method according to claim 19, The computer executes the following via a network based on the acquired information and the analysis results: Based on at least one of the rescue request reception information, the rescue operation acquisition information, and the member notification information, Performing training or updating of artificial intelligence models; A road management support method characterized by improving the accuracy of determining road disasters or the accuracy of optimizing the relief activities.

28. 20. The road management support method according to claim 19, The computer outputs the information based on the acquired information via a network. At least one of the determination result regarding the rescue operation, passable route information, or response proposal information, A road management support method characterized by transmitting the information to the portable information device carried by a field member of the road service provider.

29. 20. The road management support method according to claim 19, The computer outputs the information based on the acquired information via a network. At least one of traffic regulation information, road disaster occurrence status, estimated arrival time of the rescue vehicle, or passable route information, A road management support method characterized in that the information is transmitted to a mobile terminal device carried by a member of the road service provider.

30. 20. The road management support method according to claim 19, The computer outputs the information based on the acquired information via a network. At least one of the following information is provided: the occurrence status of road disasters, impassable locations, the implementation status of the rescue operations, or the estimated arrival time of the rescue vehicles; A road management support method characterized by transmitting the information to an external system that can be used by a road administrator, an administrative agency, or a disaster response agency.

31. 20. The road management support method according to claim 19, The computer, via a network, Based on the road disaster score, the judgment results regarding the relief activities, and information on the equipment and personnel available at each branch or base, Optimize the coordinated deployment of personnel or equipment across multiple branches or multiple municipalities, as well as the securing of accommodation or support bases for personnel, A road management support method characterized by providing passage permit information or passage restriction instructions to a passage permit management system or an entry management system for a disaster area.

32. 20. The road management support method according to claim 19, The computer, via a network, If the road disaster score exceeds a predetermined threshold, A road management support method characterized by automatically switching an operation mode from a normal mode to a disaster mode and changing the priority or notification format of information to be output.

33. 20. The road management support method according to claim 19, The computer communicates with the network via Collect information on the actual occurrence of road disasters, the results of the rescue operations, the traffic records of the rescue vehicles, and the analysis results obtained by analyzing them; This will be accumulated as learning data for the artificial intelligence model, A road management support method characterized by controlling a model update process for relearning or updating the artificial intelligence model.

34. 20. The road management support method according to claim 19, The computer, regarding information transmitted and received via a network between an external system, a mobile terminal device of a member of the road service business, or the mobile information device of a field crew of the road service business, A road management support method characterized by performing security cooperation to prevent unauthorized access, prevent tampering of communication content, or execute authentication processing.

35. 20. The road management support method according to claim 19, The computer will be able to respond to the suspension of some functions due to communication failure, power failure, or equipment failure in the event of a disaster. A road management support method characterized by providing redundancy in the event of a stoppage of the function by using other network routes (including satellite communications), alternative servers, or alternative processing mechanisms, thereby ensuring the continuity of operation of the entire system.

Images